Eran Malach

According to our database, Eran Malach authored at least 35 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Is ML-Based Cryptanalysis Inherently Limited? Simulating Cryptographic Adversaries via Gradient-Based Methods.

Avital Shafran, Eran Malach, Thomas Ristenpart, Gil Segev, Stefano Tessaro

IACR Cryptol. ePrint Arch., 2024

Loss-to-Loss Prediction: Scaling Laws for All Datasets.

David Brandfonbrener, Nikhil Anand, Nikhil Vyas, Eran Malach, Sham M. Kakade

CoRR, 2024

Mixture of Parrots: Experts improve memorization more than reasoning.

Samy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach

CoRR, 2024

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks.

Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham M. Kakade, Eran Malach, Samy Jelassi

CoRR, 2024

Don't Stop Me Now: Embedding Based Scheduling for LLMs.

Rana Shahout, Eran Malach, Chunwei Liu, Weifan Jiang, Minlan Yu, Michael Mitzenmacher

CoRR, 2024

Universal Length Generalization with Turing Programs.

Kaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach

CoRR, 2024

A New Perspective on Shampoo's Preconditioner.

Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson

CoRR, 2024

Transcendence: Generative Models Can Outperform The Experts That Train Them.

Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

On the Power of Decision Trees in Auto-Regressive Language Modeling.

Yulu Gan, Tomer Galanti, Tomaso A. Poggio, Eran Malach

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains.

Ezra Edelman, Nikolaos Tsilivis, Benjamin L. Edelman, Eran Malach, Surbhi Goel

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Auto-Regressive Next-Token Predictors are Universal Learners.

Eran Malach

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Repeat After Me: Transformers are Better than State Space Models at Copying.

Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck.

Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang

CoRR, 2023

Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD.

Etay Livne, Gal Kaplun, Eran Malach, Shai Shalev-Schwatz

CoRR, 2023

SubTuning: Efficient Finetuning for Multi-Task Learning.

Gal Kaplun, Andrey Gurevich, Tal Swisa, Mazor David, Shai Shalev-Shwartz, Eran Malach

CoRR, 2023

Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck.

Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

When Hardness of Approximation Meets Hardness of Learning.

Eran Malach, Shai Shalev-Shwartz

J. Mach. Learn. Res., 2022

Knowledge Distillation: Bad Models Can Be Good Role Models.

Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit.

Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Efficient Learning of CNNs using Patch Based Features.

Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netser, Shai Shalev-Shwartz

Proceedings of the International Conference on Machine Learning, 2022

2021

On the Power of Differentiable Learning versus PAC and SQ Learning.

Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels.

Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro

Proceedings of the 38th International Conference on Machine Learning, 2021

Computational Separation Between Convolutional and Fully-Connected Networks.

Eran Malach, Shai Shalev-Shwartz

Proceedings of the 9th International Conference on Learning Representations, 2021

The Connection Between Approximation, Depth Separation and Learnability in Neural Networks.

Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir

Proceedings of the Conference on Learning Theory, 2021

2020

The Implications of Local Correlation on Learning Some Deep Functions.

Eran Malach, Shai Shalev-Shwartz

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning Parities with Neural Networks.

Amit Daniely, Eran Malach

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Proving the Lottery Ticket Hypothesis: Pruning is All You Need.

Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir

Proceedings of the 37th International Conference on Machine Learning, 2020

ID3 Learns Juntas for Smoothed Product Distributions.

Alon Brutzkus, Amit Daniely, Eran Malach

Proceedings of the Conference on Learning Theory, 2020

2019

Learning Boolean Circuits with Neural Networks.

Eran Malach, Shai Shalev-Shwartz

CoRR, 2019

On the Optimality of Trees Generated by ID3.

Alon Brutzkus, Amit Daniely, Eran Malach

CoRR, 2019

Decoupling Gating from Linearity.

Jonathan Fiat, Eran Malach, Shai Shalev-Shwartz

CoRR, 2019

Is Deeper Better only when Shallow is Good?

Eran Malach, Shai Shalev-Shwartz

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

A Provably Correct Algorithm for Deep Learning that Actually Works.

Eran Malach, Shai Shalev-Shwartz

CoRR, 2018

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data.

Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Decoupling "when to update" from "how to update".

Eran Malach, Shai Shalev-Shwartz

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017