default search action
Eran Malach
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c18]Avital Shafran, Eran Malach, Thomas Ristenpart, Gil Segev, Stefano Tessaro:
Is ML-Based Cryptanalysis Inherently Limited? Simulating Cryptographic Adversaries via Gradient-Based Methods. CRYPTO (6) 2024: 37-71 - [c17]Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach:
Repeat After Me: Transformers are Better than State Space Models at Copying. ICML 2024 - [c16]Eran Malach:
Auto-Regressive Next-Token Predictors are Universal Learners. ICML 2024 - [i31]Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach:
Repeat After Me: Transformers are Better than State Space Models at Copying. CoRR abs/2402.01032 (2024) - [i30]Benjamin L. Edelman, Ezra Edelman, Surbhi Goel, Eran Malach, Nikolaos Tsilivis:
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains. CoRR abs/2402.11004 (2024) - [i29]Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach:
Transcendence: Generative Models Can Outperform The Experts That Train Them. CoRR abs/2406.11741 (2024) - [i28]Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson:
A New Perspective on Shampoo's Preconditioner. CoRR abs/2406.17748 (2024) - [i27]Kaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach:
Universal Length Generalization with Turing Programs. CoRR abs/2407.03310 (2024) - [i26]Yulu Gan, Tomer Galanti, Tomaso A. Poggio, Eran Malach:
On the Power of Decision Trees in Auto-Regressive Language Modeling. CoRR abs/2409.19150 (2024) - [i25]Rana Shahout, Eran Malach, Chunwei Liu, Weifan Jiang, Minlan Yu, Michael Mitzenmacher:
Don't Stop Me Now: Embedding Based Scheduling for LLMs. CoRR abs/2410.01035 (2024) - [i24]Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham M. Kakade, Eran Malach, Samy Jelassi:
LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks. CoRR abs/2410.13025 (2024) - [i23]Samy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach:
Mixture of Parrots: Experts improve memorization more than reasoning. CoRR abs/2410.19034 (2024) - [i22]Avital Shafran, Eran Malach, Thomas Ristenpart, Gil Segev, Stefano Tessaro:
Is ML-Based Cryptanalysis Inherently Limited? Simulating Cryptographic Adversaries via Gradient-Based Methods. IACR Cryptol. ePrint Arch. 2024: 1126 (2024) - 2023
- [c15]Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang:
Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck. NeurIPS 2023 - [i21]Gal Kaplun, Andrey Gurevich, Tal Swisa, Mazor David, Shai Shalev-Shwartz, Eran Malach:
SubTuning: Efficient Finetuning for Multi-Task Learning. CoRR abs/2302.06354 (2023) - [i20]Etay Livne, Gal Kaplun, Eran Malach, Shai Shalev-Schwatz:
Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD. CoRR abs/2309.01640 (2023) - [i19]Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang:
Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck. CoRR abs/2309.03800 (2023) - [i18]Eran Malach:
Auto-Regressive Next-Token Predictors are Universal Learners. CoRR abs/2309.06979 (2023) - 2022
- [j1]Eran Malach, Shai Shalev-Shwartz:
When Hardness of Approximation Meets Hardness of Learning. J. Mach. Learn. Res. 23: 91:1-91:24 (2022) - [c14]Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netser, Shai Shalev-Shwartz:
Efficient Learning of CNNs using Patch Based Features. ICML 2022: 2336-2356 - [c13]Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang:
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit. NeurIPS 2022 - [c12]Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz:
Knowledge Distillation: Bad Models Can Be Good Role Models. NeurIPS 2022 - [i17]Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz:
Knowledge Distillation: Bad Models Can Be Good Role Models. CoRR abs/2203.14649 (2022) - [i16]Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang:
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit. CoRR abs/2207.08799 (2022) - 2021
- [c11]Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir:
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. COLT 2021: 3265-3295 - [c10]Eran Malach, Shai Shalev-Shwartz:
Computational Separation Between Convolutional and Fully-Connected Networks. ICLR 2021 - [c9]Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro:
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels. ICML 2021: 7379-7389 - [c8]Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro:
On the Power of Differentiable Learning versus PAC and SQ Learning. NeurIPS 2021: 24340-24351 - [i15]Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir:
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. CoRR abs/2102.00434 (2021) - [i14]Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro:
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels. CoRR abs/2103.01210 (2021) - [i13]Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro:
On the Power of Differentiable Learning versus PAC and SQ Learning. CoRR abs/2108.04190 (2021) - 2020
- [c7]Alon Brutzkus, Amit Daniely, Eran Malach:
ID3 Learns Juntas for Smoothed Product Distributions. COLT 2020: 902-915 - [c6]Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir:
Proving the Lottery Ticket Hypothesis: Pruning is All You Need. ICML 2020: 6682-6691 - [c5]Amit Daniely, Eran Malach:
Learning Parities with Neural Networks. NeurIPS 2020 - [c4]Eran Malach, Shai Shalev-Shwartz:
The Implications of Local Correlation on Learning Some Deep Functions. NeurIPS 2020 - [i12]Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir:
Proving the Lottery Ticket Hypothesis: Pruning is All You Need. CoRR abs/2002.00585 (2020) - [i11]Amit Daniely, Eran Malach:
Learning Parities with Neural Networks. CoRR abs/2002.07400 (2020) - [i10]Eran Malach, Shai Shalev-Shwartz:
When Hardness of Approximation Meets Hardness of Learning. CoRR abs/2008.08059 (2020) - [i9]Eran Malach, Shai Shalev-Shwartz:
Computational Separation Between Convolutional and Fully-Connected Networks. CoRR abs/2010.01369 (2020)
2010 – 2019
- 2019
- [c3]Eran Malach, Shai Shalev-Shwartz:
Is Deeper Better only when Shallow is Good? NeurIPS 2019: 6426-6435 - [i8]Eran Malach, Shai Shalev-Shwartz:
Is Deeper Better only when Shallow is Good? CoRR abs/1903.03488 (2019) - [i7]Jonathan Fiat, Eran Malach, Shai Shalev-Shwartz:
Decoupling Gating from Linearity. CoRR abs/1906.05032 (2019) - [i6]Alon Brutzkus, Amit Daniely, Eran Malach:
ID3 Learns Juntas for Smoothed Product Distributions. CoRR abs/1906.08654 (2019) - [i5]Alon Brutzkus, Amit Daniely, Eran Malach:
On the Optimality of Trees Generated by ID3. CoRR abs/1907.05444 (2019) - [i4]Eran Malach, Shai Shalev-Shwartz:
Learning Boolean Circuits with Neural Networks. CoRR abs/1910.11923 (2019) - 2018
- [c2]Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz:
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data. ICLR (Poster) 2018 - [i3]Eran Malach, Shai Shalev-Shwartz:
A Provably Correct Algorithm for Deep Learning that Actually Works. CoRR abs/1803.09522 (2018) - 2017
- [c1]Eran Malach, Shai Shalev-Shwartz:
Decoupling "when to update" from "how to update". NIPS 2017: 960-970 - [i2]Eran Malach, Shai Shalev-Shwartz:
Decoupling "when to update" from "how to update". CoRR abs/1706.02613 (2017) - [i1]Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz:
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data. CoRR abs/1710.10174 (2017)
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 2024-11-30 01:12 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: