default search action
Razvan Pascanu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j9]Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar:
Promoting Exploration in Memory-Augmented Adam using Critical Momenta. Trans. Mach. Learn. Res. 2024 (2024) - [j8]Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven:
Continual Learning: Applications and the Road Forward. Trans. Mach. Learn. Res. 2024 (2024) - [c79]Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger:
Discovering modular solutions that generalize compositionally. ICLR 2024 - [c78]Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein:
Kalman Filter for Online Classification of Non-Stationary Data. ICLR 2024 - [c77]Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bosnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrovic:
Improving fine-grained understanding in image-text pre-training. ICML 2024 - [c76]Antonio Orvieto, Soham De, Caglar Gulcehre, Razvan Pascanu, Samuel L. Smith:
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues. ICML 2024 - [c75]Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem. ICML 2024 - [i119]Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bosnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrovic:
Improving fine-grained understanding in image-text pre-training. CoRR abs/2401.09865 (2024) - [i118]Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem. CoRR abs/2402.02868 (2024) - [i117]Clare Lyle, Zeyu Zheng, Khimya Khetarpal, Hado van Hasselt, Razvan Pascanu, James Martens, Will Dabney:
Disentangling the Causes of Plasticity Loss in Neural Networks. CoRR abs/2402.18762 (2024) - [i116]Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George-Cristian Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando de Freitas, Caglar Gulcehre
:
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models. CoRR abs/2402.19427 (2024) - [i115]Amal Rannen-Triki, Jörg Bornschein, Razvan Pascanu, Marcus Hutter, András György, Alexandre Galashov, Yee Whye Teh, Michalis K. Titsias:
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models. CoRR abs/2403.01518 (2024) - [i114]Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Razvan Pascanu, Pierre-Luc Bacon, Aristide Baratin:
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons. CoRR abs/2403.07688 (2024) - [i113]Aleksandar Botev, Soham De, Samuel L. Smith, Anushan Fernando, George-Cristian Muraru, Ruba Haroun, Leonard Berrada, Razvan Pascanu, Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Sertan Girgin, Olivier Bachem, Alek Andreev, Kathleen Kenealy, Thomas Mesnard, Cassidy Hardin, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Armand Joulin, Noah Fiedel, Evan Senter, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, David Budden, Arnaud Doucet, Sharad Vikram, Adam Paszke, Trevor Gale, Sebastian Borgeaud, Charlie Chen, Andy Brock, Antonia Paterson, Jenny Brennan, Meg Risdal, Raj Gundluru, Nesh Devanathan, Paul Mooney, Nilay Chauhan, Phil Culliton, Luiz GUStavo Martins, Elisa Bandy, David Huntsperger, Glenn Cameron, Arthur Zucker, Tris Warkentin, Ludovic Peran, Minh Giang, Zoubin Ghahramani, Clément Farabet, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell, Yee Whye Teh, Nando de Frietas:
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models. CoRR abs/2404.07839 (2024) - [i112]Skander Moalla, Andrea Miele, Razvan Pascanu, Caglar Gulcehre:
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO. CoRR abs/2405.00662 (2024) - [i111]Simin Fan, Razvan Pascanu, Martin Jaggi:
Deep Grokking: Would Deep Neural Networks Generalize Better? CoRR abs/2405.19454 (2024) - [i110]Federico Barbero, Andrea Banino, Steven Kapturowski, Dharshan Kumaran, João G. M. Araújo, Alex Vitvitskyi, Razvan Pascanu, Petar Velickovic:
Transformers need glasses! Information over-squashing in language tasks. CoRR abs/2406.04267 (2024) - [i109]Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu:
Attention as a Hypernetwork. CoRR abs/2406.05816 (2024) - [i108]Maciej Pióro, Maciej Wolczyk, Razvan Pascanu, Johannes von Oswald, João Sacramento:
State Soup: In-Context Skill Learning, Retrieval and Mixing. CoRR abs/2406.08423 (2024) - [i107]Wilfried Bounsi, Borja Ibarz, Andrew Dudzik, Jessica B. Hamrick, Larisa Markeeva, Alex Vitvitskyi, Razvan Pascanu, Petar Velickovic:
Transformers meet Neural Algorithmic Reasoners. CoRR abs/2406.09308 (2024) - [i106]Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre:
Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers. CoRR abs/2406.16450 (2024) - [i105]Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James Martens, Hado van Hasselt, Razvan Pascanu, Will Dabney:
Normalization and effective learning rates in reinforcement learning. CoRR abs/2407.01800 (2024) - [i104]Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre:
Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis. CoRR abs/2407.09835 (2024) - [i103]Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt, Johannes von Oswald, Razvan Pascanu, Guillaume Lajoie, João Sacramento:
When can transformers compositionally generalize in-context? CoRR abs/2407.12275 (2024) - [i102]Petar Velickovic, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu:
softmax is not enough (for sharp out-of-distribution). CoRR abs/2410.01104 (2024) - [i101]Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Velickovic:
Round and Round We Go! What makes Rotary Positional Encodings useful? CoRR abs/2410.06205 (2024) - [i100]Thomas Schmied, Fabian Paischer, Vihang Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter:
Retrieval-Augmented Decision Transformer: External Memory for In-context RL. CoRR abs/2410.07071 (2024) - [i99]Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter:
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks. CoRR abs/2410.22391 (2024) - [i98]Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani:
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset. CoRR abs/2411.04034 (2024) - 2023
- [j7]Jörg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuan Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de Las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato:
Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research. J. Mach. Learn. Res. 24: 308:1-308:77 (2023) - [c74]Alexandre Galashov, Jovana Mitrovic, Dhruva Tirumala, Yee Whye Teh, Timothy Nguyen, Arslan Chaudhry, Razvan Pascanu:
Continually learning representations at scale. CoLLAs 2023: 534-547 - [c73]Matko Bosnjak, Pierre Harvey Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic:
SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations. ICLR 2023 - [c72]Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Razvan Pascanu, Jonathan Godwin:
Pre-training via Denoising for Molecular Property Prediction. ICLR 2023 - [c71]Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney:
Understanding Plasticity in Neural Networks. ICML 2023: 23190-23211 - [c70]Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De:
Resurrecting Recurrent Neural Networks for Long Sequences. ICML 2023: 26670-26698 - [c69]Andrew Joseph Dudzik, Tamara von Glehn, Razvan Pascanu, Petar Velickovic:
Asynchronous Algorithmic Alignment With Cocycles. LoG 2023: 3 - [c68]Vladimir V. Mirjanic, Razvan Pascanu, Petar Velickovic:
Latent Space Representations of Neural Algorithmic Reasoners. LoG 2023: 10 - [c67]Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski:
The Tunnel Effect: Building Data Representations in Deep Neural Networks. NeurIPS 2023 - [c66]Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto:
Deep Reinforcement Learning with Plasticity Injection. NeurIPS 2023 - [c65]Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter:
Learning to Modulate pre-trained Models in RL. NeurIPS 2023 - [e3]Sarath Chandar, Razvan Pascanu, Hanie Sedghi, Doina Precup:
Conference on Lifelong Learning Agents, 22-25 August 2023, McGill University, Montréal, Québec, Canada. Proceedings of Machine Learning Research 232, PMLR 2023 [contents] - [i97]Matko Bosnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic:
SemPPL: Predicting pseudo-labels for better contrastive representations. CoRR abs/2301.05158 (2023) - [i96]Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney:
Understanding plasticity in neural networks. CoRR abs/2303.01486 (2023) - [i95]Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre
Resurrecting Recurrent Neural Networks for Long Sequences. CoRR abs/2303.06349 (2023) - [i94]Massimo Caccia, Alexandre Galashov, Arthur Douillard, Amal Rannen-Triki, Dushyant Rao, Michela Paganini, Laurent Charlin, Marc'Aurelio Ranzato, Razvan Pascanu:
Towards Compute-Optimal Transfer Learning. CoRR abs/2304.13164 (2023) - [i93]Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto:
Deep Reinforcement Learning with Plasticity Injection. CoRR abs/2305.15555 (2023) - [i92]Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski:
The Tunnel Effect: Building Data Representations in Deep Neural Networks. CoRR abs/2305.19753 (2023) - [i91]Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein:
Kalman Filter for Online Classification of Non-Stationary Data. CoRR abs/2306.08448 (2023) - [i90]Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter:
Learning to Modulate pre-trained Models in RL. CoRR abs/2306.14884 (2023) - [i89]Andrew Dudzik, Tamara von Glehn, Razvan Pascanu, Petar Velickovic:
Asynchronous Algorithmic Alignment with Cocycles. CoRR abs/2306.15632 (2023) - [i88]Adam Fisch, Amal Rannen-Triki, Razvan Pascanu, Jörg Bornschein, Angeliki Lazaridou, Elena Gribovskaya, Marc'Aurelio Ranzato:
Towards Robust and Efficient Continual Language Learning. CoRR abs/2307.05741 (2023) - [i87]Vladimir V. Mirjanic, Razvan Pascanu, Petar Velickovic:
Latent Space Representations of Neural Algorithmic Reasoners. CoRR abs/2307.08874 (2023) - [i86]Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar:
Promoting Exploration in Memory-Augmented Adam using Critical Momenta. CoRR abs/2307.09638 (2023) - [i85]Antonio Orvieto, Soham De, Çaglar Gülçehre, Razvan Pascanu, Samuel L. Smith:
On the Universality of Linear Recurrences Followed by Nonlinear Projections. CoRR abs/2307.11888 (2023) - [i84]Johannes von Oswald, Eyvind Niklasson, Maximilian Schlegel, Seijin Kobayashi, Nicolas Zucchet, Nino Scherrer, Nolan Miller, Mark Sandler, Blaise Agüera y Arcas, Max Vladymyrov, Razvan Pascanu, João Sacramento:
Uncovering mesa-optimization algorithms in Transformers. CoRR abs/2309.05858 (2023) - [i83]Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven:
Continual Learning: Applications and the Road Forward. CoRR abs/2311.11908 (2023) - [i82]Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger:
Discovering modular solutions that generalize compositionally. CoRR abs/2312.15001 (2023) - 2022
- [j6]Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess:
Behavior Priors for Efficient Reinforcement Learning. J. Mach. Learn. Res. 23: 221:1-221:68 (2022) - [j5]Çaglar Gülçehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matthew Hoffman, Razvan Pascanu, Arnaud Doucet:
An empirical study of implicit regularization in deep offline RL. Trans. Mach. Learn. Res. 2022 (2022) - [c64]Xu Ji, Razvan Pascanu, R. Devon Hjelm, Balaji Lakshminarayanan, Andrea Vedaldi:
Test Sample Accuracy Scales with Training Sample Density in Neural Networks. CoLLAs 2022: 629-646 - [c63]Andrei Alex Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell:
Probing Transfer in Deep Reinforcement Learning without Task Engineering. CoLLAs 2022: 1231-1254 - [c62]Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jörg Bornschein, Claudia Clopath, Yee Whye Teh, Razvan Pascanu:
When Does Re-initialization Work? ICBINB 2022: 12-26 - [c61]Seyed-Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar:
Wide Neural Networks Forget Less Catastrophically. ICML 2022: 15699-15717 - [c60]Petar Velickovic, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell:
The CLRS Algorithmic Reasoning Benchmark. ICML 2022: 22084-22102 - [c59]Florina-Cristina Calnegru
Correlation Based Semantic Transfer with Application to Domain Adaptation. ICONIP (1) 2022: 588-599 - [c58]Petar Velickovic, Matko Bosnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell:
Reasoning-Modulated Representations. LoG 2022: 50 - [c57]Bastian Rieck, Razvan Pascanu, Yuanqi Du, Hannes Stärk, Derek Lim, Chaitanya K. Joshi, Andreea Deac, Iulia Duta, Joshua Robinson, Gabriele Corso, Leonardo Cotta, Yanqiao Zhu, Kexin Huang, Michelle M. Li, Sofia Bourhim, Ilia Igashov:
The First Learning on Graphs Conference: Preface. LoG 2022: i-xxiii - [c56]Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Disentangling Transfer in Continual Reinforcement Learning. NeurIPS 2022 - [e2]Sarath Chandar, Razvan Pascanu, Doina Precup:
Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August 2022, McGill University, Montréal, Québec, Canada. Proceedings of Machine Learning Research 199, PMLR 2022 [contents] - [e1]Bastian Rieck, Razvan Pascanu:
Learning on Graphs Conference, LoG 2022, 9-12 December 2022, Virtual Event. Proceedings of Machine Learning Research 198, PMLR 2022 [contents] - [i81]Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic:
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet? CoRR abs/2201.05119 (2022) - [i80]Seyed-Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar:
Architecture Matters in Continual Learning. CoRR abs/2202.00275 (2022) - [i79]Petar Velickovic, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell:
The CLRS Algorithmic Reasoning Benchmark. CoRR abs/2205.15659 (2022) - [i78]Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Razvan Pascanu, Jonathan Godwin:
Pre-training via Denoising for Molecular Property Prediction. CoRR abs/2206.00133 (2022) - [i77]Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jörg Bornschein, Claudia Clopath
When Does Re-initialization Work? CoRR abs/2206.10011 (2022) - [i76]Çaglar Gülçehre
An Empirical Study of Implicit Regularization in Deep Offline RL. CoRR abs/2207.02099 (2022) - [i75]Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Disentangling Transfer in Continual Reinforcement Learning. CoRR abs/2209.13900 (2022) - [i74]Andrei A. Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell:
Probing Transfer in Deep Reinforcement Learning without Task Engineering. CoRR abs/2210.12448 (2022) - [i73]Jörg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuang Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de Las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato:
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research. CoRR abs/2211.11747 (2022) - 2021
- [c55]Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür, Razvan Pascanu, Hassan Ghasemzadeh:
Linear Mode Connectivity in Multitask and Continual Learning. ICLR 2021 - [c54]Florin Gogianu, Tudor Berariu, Mihaela Rosca, Claudia Clopath, Lucian Busoniu, Razvan Pascanu:
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective. ICML 2021: 3734-3744 - [c53]Stefan Daniel Dumitrescu, Petru Rebeja, Beáta Lorincz, Mihaela Gaman, Andrei-Marius Avram, Mihai Ilie, Andrei Pruteanu, Adriana Stan, Lorena Rosia, Cristina Iacobescu, Luciana Morogan, George Dima, Gabriel Marchidan, Traian Rebedea, Madalina Chitez, Dani Yogatama, Sebastian Ruder, Radu Tudor Ionescu, Razvan Pascanu, Viorica Patraucean:
LiRo: Benchmark and leaderboard for Romanian language tasks. NeurIPS Datasets and Benchmarks 2021 - [c52]Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. NeurIPS 2021: 28496-28510 - [c51]Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu, Peter E. Latham, Yee Whye Teh:
Powerpropagation: A sparsity inducing weight reparameterisation. NeurIPS 2021: 28889-28903 - [c50]Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu:
On the Role of Optimization in Double Descent: A Least Squares Study. NeurIPS 2021: 29567-29577 - [i72]Çaglar Gülçehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew W. Hoffman, Razvan Pascanu, Nando de Freitas:
Regularized Behavior Value Estimation. CoRR abs/2103.09575 (2021) - [i71]Florin Gogianu, Tudor Berariu, Mihaela Rosca, Claudia Clopath, Lucian Busoniu, Razvan Pascanu:
Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective. CoRR abs/2105.05246 (2021) - [i70]Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos:
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. CoRR abs/2105.10919 (2021) - [i69]Stanislav Fort, Andrew Brock, Razvan Pascanu, Soham De, Samuel L. Smith:
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error. CoRR abs/2105.13343 (2021) - [i68]Tudor Berariu, Wojciech Czarnecki, Soham De, Jörg Bornschein, Samuel L. Smith, Razvan Pascanu, Claudia Clopath:
A study on the plasticity of neural networks. CoRR abs/2106.00042 (2021) - [i67]Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae, Simon Osindero, Erich Elsen:
Top-KAST: Top-K Always Sparse Training. CoRR abs/2106.03517 (2021) - [i66]Xu Ji, Razvan Pascanu, R. Devon Hjelm, Andrea Vedaldi, Balaji Lakshminarayanan, Yoshua Bengio:
Predicting Unreliable Predictions by Shattering a Neural Network. CoRR abs/2106.08365 (2021) - [i65]Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu:
Task-agnostic Continual Learning with Hybrid Probabilistic Models. CoRR abs/2106.12772 (2021) - [i64]Petar Velickovic, Matko Bosnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell:
Reasoning-Modulated Representations. CoRR abs/2107.08881 (2021) - [i63]Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu:
On the Role of Optimization in Double Descent: A Least Squares Study. CoRR abs/2107.12685 (2021) - [i62]Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu, Peter E. Latham, Yee Whye Teh:
Powerpropagation: A sparsity inducing weight reparameterisation. CoRR abs/2110.00296 (2021) - [i61]Seyed-Iman Mirzadeh, Arslan Chaudhry, Huiyi Hu, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar:
Wide Neural Networks Forget Less Catastrophically. CoRR abs/2110.11526 (2021) - 2020
- [c49]Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell:
Meta-Learning with Warped Gradient Descent. ICLR 2020 - [c48]Siddhant M. Jayakumar, Wojciech M. Czarnecki, Jacob Menick, Jonathan Schwarz, Jack W. Rae, Simon Osindero, Yee Whye Teh, Tim Harley, Razvan Pascanu:
Multiplicative Interactions and Where to Find Them. ICLR 2020 - [c47]Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh:
Functional Regularisation for Continual Learning with Gaussian Processes. ICLR 2020 - [c46]Albert Gu, Çaglar Gülçehre, Thomas Paine, Matt Hoffman, Razvan Pascanu:
Improving the Gating Mechanism of Recurrent Neural Networks. ICML 2020: 3800-3809 - [c45]Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Çaglar Gülçehre, Siddhant M. Jayakumar, Max Jaderberg, Raphaël Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell:
Stabilizing Transformers for Reinforcement Learning. ICML 2020: 7487-7498 - [c44]Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae, Simon Osindero, Erich Elsen:
Top-KAST: Top-K Always Sparse Training. NeurIPS 2020 - [c43]Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh:
Understanding the Role of Training Regimes in Continual Learning. NeurIPS 2020 - [c42]Petar Velickovic, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell:
Pointer Graph Networks. NeurIPS 2020 - [i60]Petar Velickovic, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell:
Pointer Graph Networks. CoRR abs/2006.06380 (2020) - [i59]Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh:
Understanding the Role of Training Regimes in Continual Learning. CoRR abs/2006.06958 (2020) - [i58]Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin, Alexandre Galashov, Steven Kapturowski, Diana L. Borsa, Nicolas Heess, André Barreto, Razvan Pascanu:
Temporal Difference Uncertainties as a Signal for Exploration. CoRR abs/2010.02255 (2020) - [i57]Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür, Razvan Pascanu, Hassan Ghasemzadeh:
Linear Mode Connectivity in Multitask and Continual Learning. CoRR abs/2010.04495 (2020) - [i56]Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel L. Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko:
BYOL works even without batch statistics. CoRR abs/2010.10241 (2020) - [i55]Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess:
Behavior Priors for Efficient Reinforcement Learning. CoRR abs/2010.14274 (2020)
2010 – 2019
- 2019
- [c41]Wojciech M. Czarnecki, Razvan Pascanu, Simon Osindero, Siddhant M. Jayakumar, Grzegorz Swirszcz, Max Jaderberg:
Distilling Policy Distillation. AISTATS 2019: 1331-1340 - [c40]Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu, Hugo Larochelle:
A RAD approach to deep mixture models. DGS@ICLR 2019 - [c39]Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess:
Information asymmetry in KL-regularized RL. ICLR (Poster) 2019 - [c38]Çaglar Gülçehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter W. Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas:
Hyperbolic Attention Networks. ICLR (Poster) 2019 - [c37]Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell:
Meta-Learning with Latent Embedding Optimization. ICLR (Poster) 2019 - [c36]Vinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M. Botvinick, Oriol Vinyals, Peter W. Battaglia:
Deep reinforcement learning with relational inductive biases. ICLR (Poster) 2019 - [c35]Dushyant Rao, Francesco Visin, Andrei A. Rusu, Razvan Pascanu, Yee Whye Teh, Raia Hadsell:
Continual Unsupervised Representation Learning. NeurIPS 2019: 7645-7655 - [i54]Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh:
Functional Regularisation for Continual Learning using Gaussian Processes. CoRR abs/1901.11356 (2019) - [i53]Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero, Siddhant M. Jayakumar, Grzegorz Swirszcz, Max Jaderberg:
Distilling Policy Distillation. CoRR abs/1902.02186 (2019) - [i52]Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov, Leonard Hasenclever, Arun Ahuja, Greg Wayne, Razvan Pascanu, Yee Whye Teh, Nicolas Heess:
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL. CoRR abs/1903.07438 (2019) - [i51]Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu, Hugo Larochelle:
A RAD approach to deep mixture models. CoRR abs/1903.07714 (2019) - [i50]Tom Schaul, Diana Borsa, Joseph Modayil, Razvan Pascanu:
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning. CoRR abs/1904.11455 (2019) - [i49]Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess:
Information asymmetry in KL-regularized RL. CoRR abs/1905.01240 (2019) - [i48]Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alexander Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin J. Miller, Mohammad Gheshlaghi Azar, Ian Osband, Neil C. Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew M. Botvinick, Shane Legg:
Meta-learning of Sequential Strategies. CoRR abs/1905.03030 (2019) - [i47]Xu He, Jakub Sygnowski, Alexandre Galashov, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu:
Task Agnostic Continual Learning via Meta Learning. CoRR abs/1906.05201 (2019) - [i46]Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Hujun Yin, Raia Hadsell:
Meta-Learning with Warped Gradient Descent. CoRR abs/1909.00025 (2019) - [i45]Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Çaglar Gülçehre, Siddhant M. Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell:
Stabilizing Transformers for Reinforcement Learning. CoRR abs/1910.06764 (2019) - [i44]Albert Gu, Çaglar Gülçehre, Tom Le Paine, Matthew W. Hoffman, Razvan Pascanu:
Improving the Gating Mechanism of Recurrent Neural Networks. CoRR abs/1910.09890 (2019) - [i43]Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell:
Continual Unsupervised Representation Learning. CoRR abs/1910.14481 (2019) - [i42]Wojciech Marian Czarnecki, Simon Osindero, Razvan Pascanu, Max Jaderberg:
A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern. CoRR abs/1912.07559 (2019) - 2018
- [j4]Andrea Banino, Caswell Barry
Vector-based navigation using grid-like representations in artificial agents. Nat. 557(7705): 429-433 (2018) - [c34]Antonio Polino, Razvan Pascanu, Dan Alistarh:
Model compression via distillation and quantization. ICLR (Poster) 2018 - [c33]Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell:
Memory-based Parameter Adaptation. ICLR (Poster) 2018 - [c32]Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Nicolas Heess, Simon Osindero, Razvan Pascanu:
Mix & Match Agent Curricula for Reinforcement Learning. ICML 2018: 1095-1103 - [c31]Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew M. Botvinick:
Been There, Done That: Meta-Learning with Episodic Recall. ICML 2018: 4351-4360 - [c30]Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell:
Progress & Compress: A scalable framework for continual learning. ICML 2018: 4535-4544 - [c29]Adam Santoro, Ryan Faulkner, David Raposo, Jack W. Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy P. Lillicrap:
Relational recurrent neural networks. NeurIPS 2018: 7310-7321 - [i41]Antonio Polino, Razvan Pascanu, Dan Alistarh:
Model compression via distillation and quantization. CoRR abs/1802.05668 (2018) - [i40]Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell:
Memory-based Parameter Adaptation. CoRR abs/1802.10542 (2018) - [i39]Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter W. Battaglia:
Learning Deep Generative Models of Graphs. CoRR abs/1803.03324 (2018) - [i38]Yao Lu, Mehrtash Harandi, Richard I. Hartley, Razvan Pascanu:
Block Mean Approximation for Efficient Second Order Optimization. CoRR abs/1804.05484 (2018) - [i37]Thomas S. Stepleton, Razvan Pascanu, Will Dabney, Siddhant M. Jayakumar, Hubert Soyer, Rémi Munos:
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery. CoRR abs/1805.04955 (2018) - [i36]Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell:
Progress & Compress: A scalable framework for continual learning. CoRR abs/1805.06370 (2018) - [i35]Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew M. Botvinick:
Been There, Done That: Meta-Learning with Episodic Recall. CoRR abs/1805.09692 (2018) - [i34]Çaglar Gülçehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter W. Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas:
Hyperbolic Attention Networks. CoRR abs/1805.09786 (2018) - [i33]Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinícius Flores Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Çaglar Gülçehre, H. Francis Song, Andrew J. Ballard, Justin Gilmer, George E. Dahl, Ashish Vaswani, Kelsey R. Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matthew M. Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu:
Relational inductive biases, deep learning, and graph networks. CoRR abs/1806.01261 (2018) - [i32]Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Simon Osindero, Nicolas Heess, Razvan Pascanu:
Mix&Match - Agent Curricula for Reinforcement Learning. CoRR abs/1806.01780 (2018) - [i31]Adam Santoro, Ryan Faulkner, David Raposo, Jack W. Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy P. Lillicrap:
Relational recurrent neural networks. CoRR abs/1806.01822 (2018) - [i30]Vinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M. Botvinick, Oriol Vinyals, Peter W. Battaglia:
Relational Deep Reinforcement Learning. CoRR abs/1806.01830 (2018) - [i29]Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell:
Meta-Learning with Latent Embedding Optimization. CoRR abs/1807.05960 (2018) - [i28]Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar, Razvan Pascanu, Balaji Lakshminarayanan:
Adapting Auxiliary Losses Using Gradient Similarity. CoRR abs/1812.02224 (2018) - 2017
- [c28]Andrei A. Rusu, Matej Vecerík, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell:
Sim-to-Real Robot Learning from Pixels with Progressive Nets. CoRL 2017: 262-270 - [c27]Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia:
Metacontrol for Adaptive Imagination-Based Optimization. ICLR (Poster) 2017 - [c26]Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andy Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell:
Learning to Navigate in Complex Environments. ICLR (Poster) 2017 - [c25]David Raposo, Adam Santoro, David G. T. Barrett, Razvan Pascanu, Tim Lillicrap, Peter W. Battaglia:
Discovering objects and their relations from entangled scene representations. ICLR (Workshop) 2017 - [c24]Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio:
Sharp Minima Can Generalize For Deep Nets. ICML 2017: 1019-1028 - [c23]Wojciech M. Czarnecki, Simon Osindero, Max Jaderberg, Grzegorz Swirszcz, Razvan Pascanu:
Sobolev Training for Neural Networks. NIPS 2017: 4278-4287 - [c22]Yee Whye Teh, Victor Bapst, Wojciech M. Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu:
Distral: Robust multitask reinforcement learning. NIPS 2017: 4496-4506 - [c21]Nicholas Watters, Daniel Zoran, Theophane Weber, Peter W. Battaglia, Razvan Pascanu, Andrea Tacchetti:
Visual Interaction Networks: Learning a Physics Simulator from Video. NIPS 2017: 4539-4547 - [c20]Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter W. Battaglia, Tim Lillicrap:
A simple neural network module for relational reasoning. NIPS 2017: 4967-4976 - [c19]Sébastien Racanière, Theophane Weber, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter W. Battaglia, Demis Hassabis, David Silver, Daan Wierstra:
Imagination-Augmented Agents for Deep Reinforcement Learning. NIPS 2017: 5690-5701 - [i27]David Raposo, Adam Santoro, David G. T. Barrett, Razvan Pascanu, Timothy P. Lillicrap, Peter W. Battaglia:
Discovering objects and their relations from entangled scene representations. CoRR abs/1702.05068 (2017) - [i26]Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio:
Sharp Minima Can Generalize For Deep Nets. CoRR abs/1703.04933 (2017) - [i25]Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia:
Metacontrol for Adaptive Imagination-Based Optimization. CoRR abs/1705.02670 (2017) - [i24]Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter W. Battaglia, Timothy P. Lillicrap:
A simple neural network module for relational reasoning. CoRR abs/1706.01427 (2017) - [i23]Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter W. Battaglia, Daniel Zoran:
Visual Interaction Networks. CoRR abs/1706.01433 (2017) - [i22]Wojciech Marian Czarnecki, Simon Osindero, Max Jaderberg, Grzegorz Swirszcz, Razvan Pascanu:
Sobolev Training for Neural Networks. CoRR abs/1706.04859 (2017) - [i21]Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu:
Distral: Robust Multitask Reinforcement Learning. CoRR abs/1707.04175 (2017) - [i20]Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sébastien Racanière, David P. Reichert, Theophane Weber, Daan Wierstra, Peter W. Battaglia:
Learning model-based planning from scratch. CoRR abs/1707.06170 (2017) - [i19]Theophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter W. Battaglia, David Silver, Daan Wierstra:
Imagination-Augmented Agents for Deep Reinforcement Learning. CoRR abs/1707.06203 (2017) - 2016
- [c18]Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, Koray Kavukcuoglu:
Interaction Networks for Learning about Objects, Relations and Physics. NIPS 2016: 4502-4510 - [c17]Andrei A. Rusu, Sergio Gomez Colmenarejo, Çaglar Gülçehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell:
Policy Distillation. ICLR (Poster) 2016 - [i18]Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermüller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul F. Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron C. Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Melanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian J. Goodfellow, Matthew Graham, Çaglar Gülçehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrançois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Joseph Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph P. Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang:
Theano: A Python framework for fast computation of mathematical expressions. CoRR abs/1605.02688 (2016) - [i17]Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell:
Progressive Neural Networks. CoRR abs/1606.04671 (2016) - [i16]Andrei A. Rusu, Matej Vecerík, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell:
Sim-to-Real Robot Learning from Pixels with Progressive Nets. CoRR abs/1610.04286 (2016) - [i15]Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell:
Learning to Navigate in Complex Environments. CoRR abs/1611.03673 (2016) - [i14]Grzegorz Swirszcz, Wojciech Marian Czarnecki, Razvan Pascanu:
Local minima in training of deep networks. CoRR abs/1611.06310 (2016) - [i13]Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, Koray Kavukcuoglu:
Interaction Networks for Learning about Objects, Relations and Physics. CoRR abs/1612.00222 (2016) - [i12]James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell:
Overcoming catastrophic forgetting in neural networks. CoRR abs/1612.00796 (2016) - 2015
- [c16]Razvan Pascanu, Jack W. Stokes, Hermineh Sanossian, Mady Marinescu, Anil Thomas:
Malware classification with recurrent networks. ICASSP 2015: 1916-1920 - [c15]Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu:
Natural Neural Networks. NIPS 2015: 2071-2079 - [i11]Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu:
Natural Neural Networks. CoRR abs/1507.00210 (2015) - 2014
- [c14]Guido Montúfar, Razvan Pascanu, KyungHyun Cho, Yoshua Bengio:
On the Number of Linear Regions of Deep Neural Networks. NIPS 2014: 2924-2932 - [c13]Yann N. Dauphin, Razvan Pascanu, Çaglar Gülçehre, KyungHyun Cho, Surya Ganguli, Yoshua Bengio:
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. NIPS 2014: 2933-2941 - [c12]Çaglar Gülçehre
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks. ECML/PKDD (1) 2014: 530-546 - [c11]Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Yoshua Bengio:
How to Construct Deep Recurrent Neural Networks. ICLR (Poster) 2014 - [c10]Razvan Pascanu, Guido Montúfar, Yoshua Bengio:
On the number of inference regions of deep feed forward networks with piece-wise linear activations. ICLR (Poster) 2014 - [c9]Razvan Pascanu, Yoshua Bengio:
Revisiting Natural Gradient for Deep Networks. ICLR 2014 - [i10]Guido Montúfar, Razvan Pascanu, Kyunghyun Cho, Yoshua Bengio:
On the Number of Linear Regions of Deep Neural Networks. CoRR abs/1402.1869 (2014) - [i9]Razvan Pascanu, Yann N. Dauphin, Surya Ganguli, Yoshua Bengio:
On the saddle point problem for non-convex optimization. CoRR abs/1405.4604 (2014) - [i8]Yann N. Dauphin, Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Surya Ganguli, Yoshua Bengio:
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. CoRR abs/1406.2572 (2014) - 2013
- [c8]Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu:
Advances in optimizing recurrent networks. ICASSP 2013: 8624-8628 - [c7]Samira Ebrahimi Kahou, Christopher J. Pal, Xavier Bouthillier, Pierre Froumenty, Çaglar Gülçehre
Combining modality specific deep neural networks for emotion recognition in video. ICMI 2013: 543-550 - [c6]Razvan Pascanu, Tomás Mikolov, Yoshua Bengio:
On the difficulty of training recurrent neural networks. ICML (3) 2013: 1310-1318 - [c5]Guillaume Desjardins, Razvan Pascanu, Aaron C. Courville, Yoshua Bengio:
Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines. ICLR (Poster) 2013 - [c4]Razvan Pascanu, Yoshua Bengio:
Natural Gradient Revisited. ICLR (Workshop Poster) 2013 - [i7]Ian J. Goodfellow, David Warde-Farley, Pascal Lamblin, Vincent Dumoulin, Mehdi Mirza, Razvan Pascanu, James Bergstra, Frédéric Bastien, Yoshua Bengio:
Pylearn2: a machine learning research library. CoRR abs/1308.4214 (2013) - [i6]Çaglar Gülçehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio:
Learned-norm pooling for deep neural networks. CoRR abs/1311.1780 (2013) - 2012
- [j3]Hugo Larochelle, Michael I. Mandel, Razvan Pascanu, Yoshua Bengio:
Learning Algorithms for the Classification Restricted Boltzmann Machine. J. Mach. Learn. Res. 13: 643-669 (2012) - [i5]Razvan Pascanu, Tomás Mikolov, Yoshua Bengio:
Understanding the exploding gradient problem. CoRR abs/1211.5063 (2012) - [i4]Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, James Bergstra, Ian J. Goodfellow, Arnaud Bergeron, Nicolas Bouchard, David Warde-Farley, Yoshua Bengio:
Theano: new features and speed improvements. CoRR abs/1211.5590 (2012) - [i3]Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu:
Advances in Optimizing Recurrent Networks. CoRR abs/1212.0901 (2012) - 2011
- [j2]Razvan Pascanu, Herbert Jaeger:
A neurodynamical model for working memory. Neural Networks 24(2): 199-207 (2011) - [j1]Michael I. Mandel, Razvan Pascanu, Douglas Eck, Yoshua Bengio, Luca Maria Aiello
Contextual tag inference. ACM Trans. Multim. Comput. Commun. Appl. 7(Supplement): 32 (2011) - [c3]Yoshua Bengio, Frédéric Bastien, Arnaud Bergeron, Nicolas Boulanger-Lewandowski, Thomas M. Breuel, Youssouf Chherawala, Moustapha Cissé, Myriam Côté, Dumitru Erhan, Jeremy Eustache, Xavier Glorot, Xavier Muller, Sylvain Pannetier Lebeuf, Razvan Pascanu, Salah Rifai, François Savard, Guillaume Sicard:
Deep Learners Benefit More from Out-of-Distribution Examples. AISTATS 2011: 164-172 - [i2]Michael I. Mandel, Razvan Pascanu, Hugo Larochelle, Yoshua Bengio:
Autotagging music with conditional restricted Boltzmann machines. CoRR abs/1103.2832 (2011) - 2010
- [c2]Narunas Vaskevicius, Kaustubh Pathak, Razvan Pascanu, Andreas Birk
Extraction of quadrics from noisy point-clouds using a sensor noise model. ICRA 2010: 3466-3471 - [c1]James Bergstra, Olivier Breuleux, Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Desjardins, Joseph P. Turian, David Warde-Farley, Yoshua Bengio:
Theano: A CPU and GPU Math Compiler in Python. SciPy 2010: 18-24 - [i1]Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron, Nicolas Boulanger-Lewandowski, Thomas M. Breuel, Youssouf Chherawala, Moustapha Cissé, Myriam Côté, Dumitru Erhan, Jeremy Eustache, Xavier Glorot, Xavier Muller, Sylvain Pannetier Lebeuf, Razvan Pascanu, Salah Rifai, François Savard, Guillaume Sicard:
Deep Self-Taught Learning for Handwritten Character Recognition. CoRR abs/1009.3589 (2010)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-01-02 18:13 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: