default search action
Alexander Rakhlin
Sasha Rakhlin
Person information
- affiliation: MIT, Department of Brain & Cognitive Sciences, USA
- affiliation (former): University of Pennsylvania, Department of Computer and Information Science
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c85]Subhradeep Kayal, Alexander Rakhlin, Ali Dashti, Serguei Stepaniants:
How Far Is Too Far? Studying the Effects of Domain Discrepancy on Masked Language Models. LREC/COLING 2024: 8192-8199 - [c84]Adam Block, Alexander Rakhlin, Abhishek Shetty:
On the Performance of Empirical Risk Minimization with Smoothed Data. COLT 2024: 596-629 - [c83]Fan Chen, Constantinos Daskalakis, Noah Golowich, Alexander Rakhlin:
Near-Optimal Learning and Planning in Separated Latent MDPs. COLT 2024: 995-1067 - [c82]Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei:
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data. COLT 2024: 2644-2719 - [c81]Alekh Agarwal, Jian Qian, Alexander Rakhlin, Tong Zhang:
The Non-linear F-Design and Applications to Interactive Learning. ICML 2024 - [c80]Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal:
Random Latent Exploration for Deep Reinforcement Learning. ICML 2024 - [i87]Adam Block, Alexander Rakhlin, Abhishek Shetty:
On the Performance of Empirical Risk Minimization with Smoothed Data. CoRR abs/2402.14987 (2024) - [i86]Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei:
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data. CoRR abs/2403.17091 (2024) - [i85]Dylan J. Foster, Yanjun Han, Jian Qian, Alexander Rakhlin:
Online Estimation via Offline Estimation: An Information-Theoretic Framework. CoRR abs/2404.10122 (2024) - [i84]Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin:
The Power of Resets in Online Reinforcement Learning. CoRR abs/2404.15417 (2024) - [i83]Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, Alexander Rakhlin:
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF. CoRR abs/2405.21046 (2024) - [i82]Fan Chen, Constantinos Daskalakis, Noah Golowich, Alexander Rakhlin:
Near-Optimal Learning and Planning in Separated Latent MDPs. CoRR abs/2406.07920 (2024) - [i81]Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal:
Random Latent Exploration for Deep Reinforcement Learning. CoRR abs/2407.13755 (2024) - [i80]Fan Chen, Dylan J. Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu:
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability. CoRR abs/2410.05117 (2024) - [i79]Zeyu Jia, Jian Qian, Alexander Rakhlin, Chen-Yu Wei:
How Does Variance Shape the Regret in Contextual Bandits? CoRR abs/2410.12713 (2024) - [i78]Jian Qian, Alexander Rakhlin, Nikita Zhivotovskiy:
Refined Risk Bounds for Unbounded Losses via Transductive Priors. CoRR abs/2410.21621 (2024) - 2023
- [c79]Adam Block, Max Simchowitz, Alexander Rakhlin:
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making. COLT 2023: 1618-1665 - [c78]Dean P. Foster, Dylan J. Foster, Noah Golowich, Alexander Rakhlin:
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring. COLT 2023: 2678-2792 - [c77]Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin:
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL. ICML 2023: 24659-24700 - [c76]Dylan J. Foster, Noah Golowich, Jian Qian, Alexander Rakhlin, Ayush Sekhari:
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient. NeurIPS 2023 - [c75]Zeyu Jia, Gene Li, Alexander Rakhlin, Ayush Sekhari, Nati Srebro:
When is Agnostic Reinforcement Learning Statistically Tractable? NeurIPS 2023 - [c74]Gil Kur, Eli Putterman, Alexander Rakhlin:
On the Variance, Admissibility, and Stability of Empirical Risk Minimization. NeurIPS 2023 - [c73]Haochuan Li, Jian Qian, Yi Tian, Alexander Rakhlin, Ali Jadbabaie:
Convex and Non-convex Optimization Under Generalized Smoothness. NeurIPS 2023 - [c72]Haochuan Li, Alexander Rakhlin, Ali Jadbabaie:
Convergence of Adam Under Relaxed Assumptions. NeurIPS 2023 - [c71]Zakaria Mhammedi, Adam Block, Dylan J. Foster, Alexander Rakhlin:
Efficient Model-Free Exploration in Low-Rank MDPs. NeurIPS 2023 - [i77]Adam Block, Alexander Rakhlin, Max Simchowitz:
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making. CoRR abs/2302.05430 (2023) - [i76]Margalit Glasgow, Alexander Rakhlin:
Lower Bounds for γ-Regret via the Decision-Estimation Coefficient. CoRR abs/2303.03327 (2023) - [i75]Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin:
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL. CoRR abs/2304.05889 (2023) - [i74]Haochuan Li, Ali Jadbabaie, Alexander Rakhlin:
Convergence of Adam Under Relaxed Assumptions. CoRR abs/2304.13972 (2023) - [i73]Dylan J. Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin:
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring. CoRR abs/2305.00684 (2023) - [i72]Gil Kur, Eli Putterman, Alexander Rakhlin:
On the Variance, Admissibility, and Stability of Empirical Risk Minimization. CoRR abs/2305.18508 (2023) - [i71]Haochuan Li, Jian Qian, Yi Tian, Alexander Rakhlin, Ali Jadbabaie:
Convex and Non-Convex Optimization under Generalized Smoothness. CoRR abs/2306.01264 (2023) - [i70]Zakaria Mhammedi, Adam Block, Dylan J. Foster, Alexander Rakhlin:
Efficient Model-Free Exploration in Low-Rank MDPs. CoRR abs/2307.03997 (2023) - [i69]Zeyu Jia, Gene Li, Alexander Rakhlin, Ayush Sekhari, Nathan Srebro:
When is Agnostic Reinforcement Learning Statistically Tractable? CoRR abs/2310.06113 (2023) - [i68]Dylan J. Foster, Alexander Rakhlin:
Foundations of Reinforcement Learning and Interactive Decision Making. CoRR abs/2312.16730 (2023) - 2022
- [j16]Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin:
Intrinsic Dimension Estimation Using Wasserstein Distance. J. Mach. Learn. Res. 23: 313:1-313:37 (2022) - [c70]Adam Block, Yuval Dagan, Noah Golowich, Alexander Rakhlin:
Smoothed Online Learning is as Easy as Statistical Learning. COLT 2022: 1716-1786 - [c69]Zakaria Mhammedi, Alexander Rakhlin:
Damped Online Newton Step for Portfolio Selection. COLT 2022: 5561-5595 - [c68]Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan:
On the Complexity of Adversarial Decision Making. NeurIPS 2022 - [i67]Adam Block, Yuval Dagan, Noah Golowich, Alexander Rakhlin:
Smoothed Online Learning is as Easy as Statistical Learning. CoRR abs/2202.04690 (2022) - [i66]Zakaria Mhammedi, Alexander Rakhlin:
Damped Online Newton Step for Portfolio Selection. CoRR abs/2202.07574 (2022) - [i65]Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin:
Rate of convergence of the smoothed empirical Wasserstein distance. CoRR abs/2205.02128 (2022) - [i64]Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan:
On the Complexity of Adversarial Decision Making. CoRR abs/2206.13063 (2022) - [i63]Dylan J. Foster, Noah Golowich, Jian Qian, Alexander Rakhlin, Ayush Sekhari:
A Note on Model-Free Reinforcement Learning with the Decision-Estimation Coefficient. CoRR abs/2211.14250 (2022) - 2021
- [j15]Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin:
Deep learning: a statistical viewpoint. Acta Numer. 30: 87-201 (2021) - [j14]Tuhin Sarkar, Alexander Rakhlin, Munther A. Dahleh:
Finite Time LTI System Identification. J. Mach. Learn. Res. 22: 26:1-26:61 (2021) - [c67]Adam Block, Yuval Dagan, Alexander Rakhlin:
Majorizing Measures, Sequential Complexities, and Online Learning. COLT 2021: 587-590 - [c66]Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu:
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective. COLT 2021: 2059 - [c65]Gil Kur, Alexander Rakhlin:
On the Minimal Error of Empirical Risk Minimization. COLT 2021: 2849-2852 - [c64]Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean P. Foster, Daniel N. Hill, Inderjit S. Dhillon:
Top-k eXtreme Contextual Bandits with Arm Hierarchy. ICML 2021: 9422-9433 - [p1]Isabel Amaya-Rodriguez, Javier Civit-Masot, Francisco Luna-Perejon, Lourdes Duran-Lopez, Alexander Rakhlin, Sergey I. Nikolenko, Satoshi Kondo, Pablo Laiz, Jordi Vitrià, Santi Seguí, Patrick Brandao:
ResNet. Computer-Aided Analysis of Gastrointestinal Videos 2021: 99-114 - [i62]Adam Block, Yuval Dagan, Sasha Rakhlin:
Majorizing Measures, Sequential Complexities, and Online Learning. CoRR abs/2102.01729 (2021) - [i61]Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean P. Foster, Daniel N. Hill, Inderjit S. Dhillon:
Top-k eXtreme Contextual Bandits with Arm Hierarchy. CoRR abs/2102.07800 (2021) - [i60]Gil Kur, Alexander Rakhlin:
On the Minimal Error of Empirical Risk Minimization. CoRR abs/2102.12066 (2021) - [i59]Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin:
Deep learning: a statistical viewpoint. CoRR abs/2103.09177 (2021) - [i58]Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin:
Intrinsic Dimension Estimation. CoRR abs/2106.04018 (2021) - [i57]Dean P. Foster, Alexander Rakhlin:
On Submodular Contextual Bandits. CoRR abs/2112.02165 (2021) - [i56]Dylan J. Foster, Sham M. Kakade, Jian Qian, Alexander Rakhlin:
The Statistical Complexity of Interactive Decision Making. CoRR abs/2112.13487 (2021) - 2020
- [j13]Katja Ovchinnikova, Lachlan Stuart, Alexander Rakhlin, Sergey I. Nikolenko
, Theodore Alexandrov:
ColocML: machine learning quantifies co-localization between mass spectrometry images. Bioinform. 36(10): 3215-3224 (2020) - [j12]T. Tony Cai, Tengyuan Liang, Alexander Rakhlin:
Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information. J. Mach. Learn. Res. 21: 11:1-11:34 (2020) - [c63]Gil Kur, Alexander Rakhlin, Adityanand Guntuboyina:
On Suboptimality of Least Squares with Application to Estimation of Convex Bodies. COLT 2020: 2406-2424 - [c62]Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai:
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. COLT 2020: 2683-2711 - [c61]Dylan J. Foster, Alexander Rakhlin:
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles. ICML 2020: 3199-3210 - [c60]Dylan J. Foster, Tuhin Sarkar, Alexander Rakhlin:
Learning nonlinear dynamical systems from a single trajectory. L4DC 2020: 851-861 - [c59]Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford:
Learning the Linear Quadratic Regulator from Nonlinear Observations. NeurIPS 2020 - [i55]Adam Block, Youssef Mroueh, Alexander Rakhlin:
Generative Modeling with Denoising Auto-Encoders and Langevin Sampling. CoRR abs/2002.00107 (2020) - [i54]Dylan J. Foster, Alexander Rakhlin:
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles. CoRR abs/2002.04926 (2020) - [i53]Dylan J. Foster, Alexander Rakhlin, Tuhin Sarkar:
Learning nonlinear dynamical systems from a single trajectory. CoRR abs/2004.14681 (2020) - [i52]Gil Kur, Alexander Rakhlin, Adityanand Guntuboyina:
On Suboptimality of Least Squares with Application to Estimation of Convex Bodies. CoRR abs/2006.04046 (2020) - [i51]Adam Block, Youssef Mroueh, Alexander Rakhlin, Jerret Ross:
Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis. CoRR abs/2006.11166 (2020) - [i50]Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu:
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective. CoRR abs/2010.03104 (2020) - [i49]Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford:
Learning the Linear Quadratic Regulator from Nonlinear Observations. CoRR abs/2010.03799 (2020)
2010 – 2019
- 2019
- [c58]Tengyuan Liang, Tomaso A. Poggio, Alexander Rakhlin, James Stokes:
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. AISTATS 2019: 888-896 - [c57]Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov:
Does data interpolation contradict statistical optimality? AISTATS 2019: 1611-1619 - [c56]Tuhin Sarkar, Alexander Rakhlin, Munther A. Dahleh:
Nonparametric System identification of Stochastic Switched Linear Systems. CDC 2019: 3623-3628 - [c55]Alexander Rakhlin, Xiyu Zhai:
Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon. COLT 2019: 2595-2623 - [c54]Alexander Rakhlin, Aleksei Tiulpin, Alexey A. Shvets, Alexandr A. Kalinin, Vladimir I. Iglovikov, Sergey I. Nikolenko:
Breast Tumor Cellularity Assessment Using Deep Neural Networks. ICCV Workshops 2019: 371-380 - [c53]Tuhin Sarkar, Alexander Rakhlin:
Near optimal finite time identification of arbitrary linear dynamical systems. ICML 2019: 5610-5618 - [i48]Tuhin Sarkar, Alexander Rakhlin, Munther A. Dahleh:
Finite-Time System Identification for Partially Observed LTI Systems of Unknown Order. CoRR abs/1902.01848 (2019) - [i47]Alexander Rakhlin, Alexey A. Shvets, Alexandr A. Kalinin, Aleksei Tiulpin, Vladimir I. Iglovikov, Sergey I. Nikolenko:
Breast Tumor Cellularity Assessment using Deep Neural Networks. CoRR abs/1905.01743 (2019) - [i46]Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai:
On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. CoRR abs/1908.10292 (2019) - [i45]Tuhin Sarkar, Alexander Rakhlin, Munther A. Dahleh:
Nonparametric System identification of Stochastic Switched Linear Systems. CoRR abs/1909.04617 (2019) - [i44]Dylan J. Foster, Alexander Rakhlin:
𝓁∞ Vector Contraction for Rademacher Complexity. CoRR abs/1911.06468 (2019) - 2018
- [c52]Noah Golowich, Alexander Rakhlin, Ohad Shamir:
Size-Independent Sample Complexity of Neural Networks. COLT 2018: 297-299 - [c51]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
Online Learning: Sufficient Statistics and the Burkholder Method. COLT 2018: 3028-3064 - [c50]Alexander Rakhlin, Alex Davydow, Sergey I. Nikolenko
Land Cover Classification From Satellite Imagery With U-Net and Lovasz-Softmax Loss. CVPR Workshops 2018: 262-266 - [c49]Alexander Rakhlin, Alexey Shvets, Vladimir Iglovikov, Alexandr A. Kalinin:
Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis. ICIAR 2018: 737-744 - [c48]Alexey A. Shvets, Vladimir I. Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin:
Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks. ICMLA 2018: 612-617 - [c47]Alexey A. Shvets, Alexander Rakhlin, Alexandr A. Kalinin, Vladimir I. Iglovikov:
Automatic Instrument Segmentation in Robot-Assisted Surgery using Deep Learning. ICMLA 2018: 624-628 - [c46]Vladimir I. Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin, Alexey A. Shvets:
Paediatric Bone Age Assessment Using Deep Convolutional Neural Networks. DLMIA/ML-CDS@MICCAI 2018: 300-308 - [i43]Chiyuan Zhang, Qianli Liao, Alexander Rakhlin, Brando Miranda, Noah Golowich, Tomaso A. Poggio:
Theory of Deep Learning IIb: Optimization Properties of SGD. CoRR abs/1801.02254 (2018) - [i42]Alexander Rakhlin, Alexey Shvets, Vladimir Iglovikov, Alexandr A. Kalinin:
Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis. CoRR abs/1802.00752 (2018) - [i41]Alexey Shvets, Alexander Rakhlin, Alexandr A. Kalinin, Vladimir Iglovikov:
Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning. CoRR abs/1803.01207 (2018) - [i40]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
Online Learning: Sufficient Statistics and the Burkholder Method. CoRR abs/1803.07617 (2018) - [i39]Alexey Shvets, Vladimir Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin:
Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks. CoRR abs/1804.08024 (2018) - [i38]Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov:
Does data interpolation contradict statistical optimality? CoRR abs/1806.09471 (2018) - [i37]Tengyuan Liang, Alexander Rakhlin:
Just Interpolate: Kernel "Ridgeless" Regression Can Generalize. CoRR abs/1808.00387 (2018) - [i36]Tuhin Sarkar, Alexander Rakhlin:
How fast can linear dynamical systems be learned? CoRR abs/1812.01251 (2018) - [i35]Alexander Rakhlin, Xiyu Zhai:
Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon. CoRR abs/1812.11167 (2018) - 2017
- [j11]Hariharan Narayanan, Alexander Rakhlin:
Efficient Sampling from Time-Varying Log-Concave Distributions. J. Mach. Learn. Res. 18: 112:1-112:29 (2017) - [j10]T. Tony Cai, Tengyuan Liang, Alexander Rakhlin:
On Detection and Structural Reconstruction of Small-World Random Networks. IEEE Trans. Netw. Sci. Eng. 4(3): 165-176 (2017) - [c45]Alexander Rakhlin, Karthik Sridharan:
Efficient Online Multiclass Prediction on Graphs via Surrogate Losses. AISTATS 2017: 1403-1411 - [c44]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
ZigZag: A New Approach to Adaptive Online Learning. COLT 2017: 876-924 - [c43]Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky:
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. COLT 2017: 1674-1703 - [c42]Alexander Rakhlin, Karthik Sridharan:
On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities. COLT 2017: 1704-1722 - [c41]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Multi-armed bandits in multi-agent networks. ICASSP 2017: 2786-2790 - [e2]Oren Anava, Azadeh Khaleghi, Marco Cuturi, Vitaly Kuznetsov, Alexander Rakhlin:
Proceedings of the NIPS 2016 Time Series Workshop, co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 9, 2016. JMLR Workshop and Conference Proceedings 55, JMLR.org 2017 [contents] - [i34]Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky:
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. CoRR abs/1702.03849 (2017) - [i33]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
ZigZag: A new approach to adaptive online learning. CoRR abs/1704.04010 (2017) - [i32]Tengyuan Liang, Tomaso A. Poggio, Alexander Rakhlin, James Stokes:
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. CoRR abs/1711.01530 (2017) - [i31]Vladimir Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin, Alexey Shvets:
Pediatric Bone Age Assessment Using Deep Convolutional Neural Networks. CoRR abs/1712.05053 (2017) - [i30]Noah Golowich, Alexander Rakhlin, Ohad Shamir:
Size-Independent Sample Complexity of Neural Networks. CoRR abs/1712.06541 (2017) - 2016
- [j9]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Distributed Detection: Finite-Time Analysis and Impact of Network Topology. IEEE Trans. Autom. Control. 61(11): 3256-3268 (2016) - [c40]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Distributed estimation of dynamic parameters: Regret analysis. ACC 2016: 1066-1071 - [c39]Vitaly Feldman, Alexander Rakhlin:
Conference on Learning Theory 2016: Preface. COLT 2016: 1-3 - [c38]Alexander Rakhlin, Karthik Sridharan:
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits. ICML 2016: 1977-1985 - [c37]Maxim Raginsky, Alexander Rakhlin, Matthew Tsao, Yihong Wu, Aolin Xu:
Information-theoretic analysis of stability and bias of learning algorithms. ITW 2016: 26-30 - [e1]Vitaly Feldman, Alexander Rakhlin, Ohad Shamir:
Proceedings of the 29th Conference on Learning Theory, COLT 2016, New York, USA, June 23-26, 2016. JMLR Workshop and Conference Proceedings 49, JMLR.org 2016 [contents] - [i29]Alexander Rakhlin, Karthik Sridharan:
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits. CoRR abs/1602.02196 (2016) - [i28]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Distributed Estimation of Dynamic Parameters : Regret Analysis. CoRR abs/1603.00576 (2016) - [i27]T. Tony Cai, Tengyuan Liang, Alexander Rakhlin:
On Detection and Structural Reconstruction of Small-World Random Networks. CoRR abs/1604.06474 (2016) - [i26]Alexander Rakhlin, Karthik Sridharan:
A Tutorial on Online Supervised Learning with Applications to Node Classification in Social Networks. CoRR abs/1608.09014 (2016) - 2015
- [j8]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online learning via sequential complexities. J. Mach. Learn. Res. 16: 155-186 (2015) - [c36]Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour, Karthik Sridharan:
Online Optimization : Competing with Dynamic Comparators. AISTATS 2015 - [c35]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Finite-time analysis of the distributed detection problem. Allerton 2015: 598-603 - [c34]Alexandre Belloni, Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin:
Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions. COLT 2015: 240-265 - [c33]Tengyuan Liang, Alexander Rakhlin, Karthik Sridharan:
Learning with Square Loss: Localization through Offset Rademacher Complexity. COLT 2015: 1260-1285 - [c32]Alexander Rakhlin, Karthik Sridharan:
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints. COLT 2015: 1457-1479 - [c31]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
Adaptive Online Learning. NIPS 2015: 3375-3383 - [i25]Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour, Karthik Sridharan:
Online Optimization : Competing with Dynamic Comparators. CoRR abs/1501.06225 (2015) - [i24]Alexander Rakhlin, Karthik Sridharan:
Online Nonparametric Regression with General Loss Functions. CoRR abs/1501.06598 (2015) - [i23]Alexandre Belloni, Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin:
Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions. CoRR abs/1501.07242 (2015) - [i22]Alexander Rakhlin, Karthik Sridharan:
Sequential Probability Assignment with Binary Alphabets and Large Classes of Experts. CoRR abs/1501.07340 (2015) - [i21]Tengyuan Liang, Alexander Rakhlin, Karthik Sridharan:
Learning with Square Loss: Localization through Offset Rademacher Complexity. CoRR abs/1502.06134 (2015) - [i20]Alexander Rakhlin, Karthik Sridharan:
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints. CoRR abs/1503.01212 (2015) - [i19]Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan:
Adaptive Online Learning. CoRR abs/1508.05170 (2015) - [i18]Alexander Rakhlin, Karthik Sridharan:
On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities. CoRR abs/1510.03925 (2015) - [i17]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Finite-time Analysis of the Distributed Detection Problem. CoRR abs/1512.09311 (2015) - 2014
- [j7]Gábor Bartók, Dean P. Foster, Dávid Pál, Alexander Rakhlin, Csaba Szepesvári:
Partial Monitoring - Classification, Regret Bounds, and Algorithms. Math. Oper. Res. 39(4): 967-997 (2014) - [c30]Alexander Rakhlin, Karthik Sridharan:
Online Non-Parametric Regression. COLT 2014: 1232-1264 - [i16]Alexander Rakhlin, Karthik Sridharan:
Online Nonparametric Regression. CoRR abs/1402.2594 (2014) - [i15]Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin:
On Zeroth-Order Stochastic Convex Optimization via Random Walks. CoRR abs/1402.2667 (2014) - [i14]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Distributed Detection : Finite-time Analysis and Impact of Network Topology. CoRR abs/1409.8606 (2014) - 2013
- [j6]Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin:
Stochastic Convex Optimization with Bandit Feedback. SIAM J. Optim. 23(1): 213-240 (2013) - [c29]Alexander Rakhlin, Ohad Shamir, Karthik Sridharan:
Localization and Adaptation in Online Learning. AISTATS 2013: 516-526 - [c28]Wei Han, Alexander Rakhlin, Karthik Sridharan:
Competing With Strategies. COLT 2013: 966-992 - [c27]Alexander Rakhlin, Karthik Sridharan:
Online Learning with Predictable Sequences. COLT 2013: 993-1019 - [c26]Alexander Rakhlin, Karthik Sridharan:
On Semi-Probabilistic universal prediction. ITW 2013: 1-5 - [c25]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Online Learning of Dynamic Parameters in Social Networks. NIPS 2013: 2013-2021 - [c24]Alexander Rakhlin, Karthik Sridharan:
Optimization, Learning, and Games with Predictable Sequences. NIPS 2013: 3066-3074 - [i13]Wei Han, Alexander Rakhlin, Karthik Sridharan:
Competing With Strategies. CoRR abs/1302.2672 (2013) - [i12]Alexander Rakhlin, Karthik Sridharan, Alexandre B. Tsybakov:
Empirical Entropy, Minimax Regret and Minimax Risk. CoRR abs/1308.1147 (2013) - [i11]Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie:
Online Learning of Dynamic Parameters in Social Networks. CoRR abs/1310.0432 (2013) - [i10]Alexander Rakhlin, Karthik Sridharan:
Optimization, Learning, and Games with Predictable Sequences. CoRR abs/1311.1869 (2013) - 2012
- [j5]Alexander Rakhlin:
Foreword. J. Comput. Syst. Sci. 78(5): 1403 (2012) - [j4]Sanjit A. Seshia, Alexander Rakhlin:
Quantitative Analysis of Systems Using Game-Theoretic Learning. ACM Trans. Embed. Comput. Syst. 11(S2): 55:1-55:27 (2012) - [j3]Jacob D. Abernethy, Elad Hazan
Interior-Point Methods for Full-Information and Bandit Online Learning. IEEE Trans. Inf. Theory 58(7): 4164-4175 (2012) - [c23]Alexander Rakhlin, Ohad Shamir, Karthik Sridharan:
Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization. ICML 2012 - [c22]Alexander Rakhlin, Ohad Shamir, Karthik Sridharan:
Relax and Randomize : From Value to Algorithms. NIPS 2012: 2150-2158 - [c21]Dean P. Foster, Alexander Rakhlin:
No Internal Regret via Neighborhood Watch. AISTATS 2012: 382-390 - [i9]Alexander Rakhlin, Ohad Shamir, Karthik Sridharan:
Relax and Localize: From Value to Algorithms. CoRR abs/1204.0870 (2012) - [i8]Alexander Rakhlin, Karthik Sridharan:
Online Learning with Predictable Sequences. CoRR abs/1208.3728 (2012) - 2011
- [j2]Maxim Raginsky, Alexander Rakhlin:
Information-Based Complexity, Feedback and Dynamics in Convex Programming. IEEE Trans. Inf. Theory 57(10): 7036-7056 (2011) - [c20]Maxim Raginsky, Alexander Rakhlin:
Lower Bounds for Passive and Active Learning. NIPS 2011: 1026-1034 - [c19]Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin:
Stochastic convex optimization with bandit feedback. NIPS 2011: 1035-1043 - [c18]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Stochastic, Constrained, and Smoothed Adversaries. NIPS 2011: 1764-1772 - [c17]Dean P. Foster, Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Complexity-Based Approach to Calibration with Checking Rules. COLT 2011: 293-314 - [c16]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Beyond Regret. COLT 2011: 559-594 - [i7]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Stochastic and Constrained Adversaries. CoRR abs/1104.5070 (2011) - [i6]Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin:
Stochastic convex optimization with bandit feedback. CoRR abs/1107.1744 (2011) - [i5]Dean P. Foster, Alexander Rakhlin:
No Internal Regret via Neighborhood Watch. CoRR abs/1108.6088 (2011) - 2010
- [c15]Maxim Raginsky, Alexander Rakhlin, Serdar Yüksel:
Online Convex Programming and regularization in adaptive control. CDC 2010: 1957-1962 - [c14]Hariharan Narayanan, Alexander Rakhlin:
Random Walk Approach to Regret Minimization. NIPS 2010: 1777-1785 - [c13]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Random Averages, Combinatorial Parameters, and Learnability. NIPS 2010: 1984-1992 - [i4]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Random Averages, Combinatorial Parameters, and Learnability. CoRR abs/1006.1138 (2010) - [i3]Maxim Raginsky, Alexander Rakhlin:
Information-based complexity, feedback and dynamics in sequential convex programming. CoRR abs/1010.2285 (2010) - [i2]Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari:
Online Learning: Beyond Regret. CoRR abs/1011.3168 (2010)
2000 – 2009
- 2009
- [c12]Maxim Raginsky, Alexander Rakhlin:
Information complexity of black-box convex optimization: A new look via feedback information theory. Allerton 2009: 803-510 - [c11]Jacob D. Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin:
A Stochastic View of Optimal Regret through Minimax Duality. COLT 2009 - [c10]Jacob D. Abernethy, Alexander Rakhlin:
Beating the Adaptive Bandit with High Probability. COLT 2009 - [c9]Jacob D. Abernethy, Alexander Rakhlin:
An Efficient Bandit Algorithm for sqrt(T) Regret in Online Multiclass Prediction?. COLT 2009 - [i1]Jacob D. Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin:
A Stochastic View of Optimal Regret through Minimax Duality. CoRR abs/0903.5328 (2009) - 2008
- [c8]Jacob D. Abernethy, Elad Hazan, Alexander Rakhlin:
Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization. COLT 2008: 263-274 - [c7]Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, Sham M. Kakade, Alexander Rakhlin, Ambuj Tewari:
High-Probability Regret Bounds for Bandit Online Linear Optimization. COLT 2008: 335-342 - [c6]Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin, Ambuj Tewari:
Optimal Stragies and Minimax Lower Bounds for Online Convex Games. COLT 2008: 415-424 - [c5]Sanjit A. Seshia, Alexander Rakhlin:
Game-theoretic timing analysis. ICCAD 2008: 575-582 - 2007
- [c4]Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin:
Multitask Learning with Expert Advice. COLT 2007: 484-498 - [c3]Alexander Rakhlin, Jacob D. Abernethy, Peter L. Bartlett
Online discovery of similarity mappings. ICML 2007: 767-774 - [c2]Peter L. Bartlett, Elad Hazan, Alexander Rakhlin:
Adaptive Online Gradient Descent. NIPS 2007: 65-72 - 2006
- [j1]Andrea Caponnetto, Alexander Rakhlin:
Stability Properties of Empirical Risk Minimization over Donsker Classes. J. Mach. Learn. Res. 7: 2565-2583 (2006) - [c1]Alexander Rakhlin, Andrea Caponnetto:
Stability of $K$-Means Clustering. NIPS 2006: 1121-1128
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 2024-12-01 00:18 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: