Zeyuan Allen-Zhu

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 62

Top Topics

Recurrent Neural Networks

Principal Component Regression

Stochastic Gradient

Top Venues

Publications

Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu
Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process. CoRR (2024)
Olga Golovneva, Zeyuan Allen-Zhu, Jason Weston, Sainbayar Sukhbaatar
Reverse Training to Nurse the Reversal Curse. CoRR (2024)
Zeyuan Allen-Zhu, Yuanzhi Li
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws. CoRR (2024)
Zeyuan Allen-Zhu, Yuanzhi Li
Physics of Language Models: Part 3.2, Knowledge Manipulation. CoRR (2023)
Zeyuan Allen-Zhu, Yuanzhi Li
Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning. COLT (2023)
Cathy Li, Jana Sotáková, Emily Wenger, Zeyuan Allen-Zhu, François Charton, Kristin E. Lauter
SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets. CoRR (2023)
Cathy Yuanchen Li, Emily Wenger, Zeyuan Allen-Zhu, François Charton, Kristin E. Lauter
SALSA VERDE: a machine learning attack on LWE with sparse small secrets. NeurIPS (2023)
Cathy Li, Jana Sotáková, Emily Wenger, Zeyuan Allen-Zhu, François Charton, Kristin E. Lauter
SALSA VERDE: a machine learning attack on Learning with Errors with sparse small secrets. IACR Cryptol. ePrint Arch. 2023 (2023)
Zeyuan Allen-Zhu, Yuanzhi Li
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions. ICLR (2023)
Zeyuan Allen-Zhu, Yuanzhi Li
Physics of Language Models: Part 1, Context-Free Grammar. CoRR (2023)
Zeyuan Allen-Zhu, Yuanzhi Li
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. ICLR (2023)
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen
LoRA: Low-Rank Adaptation of Large Language Models. ICLR (2022)
Zeyuan Allen-Zhu, Yuanzhi Li
Feature Purification: How Adversarial Training Performs Robust Deep Learning. FOCS (2022)
Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang
Near-optimal discrete optimization for experimental design: a regret minimization approach. Math. Program. 186 (1) (2021)
Zeyuan Allen-Zhu, Yuanzhi Li
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions. CoRR (2021)
Zeyuan Allen-Zhu, Yuanzhi Li
Feature Purification: How Adversarial Training Performs Robust Deep Learning. FOCS (2021)
Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh
Byzantine-Resilient Non-Convex Stochastic Gradient Descent. ICLR (2021)
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Weizhu Chen
LoRA: Low-Rank Adaptation of Large Language Models. CoRR (2021)
Zeyuan Allen-Zhu, Yuanzhi Li
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. CoRR (2020)
Zeyuan Allen-Zhu, Faeze Ebrahimian, Jerry Li, Dan Alistarh
Byzantine-Resilient Non-Convex Stochastic Gradient Descent. CoRR (2020)
Zeyuan Allen-Zhu, Yuanzhi Li
Feature Purification: How Adversarial Training Performs Robust Deep Learning. CoRR (2020)
Zeyuan Allen-Zhu, Yuanzhi Li
Backward Feature Correction: How Deep Learning Performs Deep Learning. CoRR (2020)
Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers. NeurIPS (2019)
Zeyuan Allen-Zhu, Lorenzo Orecchia
Nearly linear-time packing and covering LP solvers - Achieving width-independence and -convergence. Math. Program. 175 (1-2) (2019)
Zeyuan Allen-Zhu, Yuanzhi Li
Can SGD Learn Recurrent Neural Networks with Provable Generalization? CoRR (2019)
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
On the Convergence Rate of Training Recurrent Neural Networks. NeurIPS (2019)
Zeyuan Allen-Zhu, Yuanzhi Li
Can SGD Learn Recurrent Neural Networks with Provable Generalization? NeurIPS (2019)
Zeyuan Allen-Zhu, Yuanzhi Li
What Can ResNet Learn Efficiently, Going Beyond Kernels? NeurIPS (2019)
Zeyuan Allen-Zhu, Yuanzhi Li
What Can ResNet Learn Efficiently, Going Beyond Kernels? CoRR (2019)
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
A Convergence Theory for Deep Learning via Over-Parameterization. ICML (2019)
Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang
The Lingering of Gradients: How to Reuse Gradients over Time. CoRR (2019)
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
A Convergence Theory for Deep Learning via Over-Parameterization. CoRR (2018)
Zeyuan Allen-Zhu
How To Make the Gradients Small Stochastically. CoRR (2018)
Zeyuan Allen-Zhu, Ankit Garg, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson
Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing. STOC (2018)
Zeyuan Allen-Zhu, Ankit Garg, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson
Operator Scaling via Geodesically Convex Optimization, Invariant Theory and Polynomial Identity Testing. CoRR (2018)
Zeyuan Allen-Zhu, Sébastien Bubeck, Yuanzhi Li
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits. CoRR (2018)
Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang
The Lingering of Gradients: How to Reuse Gradients Over Time. NeurIPS (2018)
Dan Alistarh, Zeyuan Allen-Zhu, Jerry Li
Byzantine Stochastic Gradient Descent. CoRR (2018)
Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers. CoRR (2018)
Chi Jin, Zeyuan Allen-Zhu, Sébastien Bubeck, Michael I. Jordan
Is Q-learning Provably Efficient? CoRR (2018)
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
On the Convergence Rate of Training Recurrent Neural Networks. CoRR (2018)
Zeyuan Allen-Zhu
Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization. ICML (2018)
Zeyuan Allen-Zhu
Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization. CoRR (2018)
Dan Alistarh, Zeyuan Allen-Zhu, Jerry Li
Byzantine Stochastic Gradient Descent. NeurIPS (2018)
Zeyuan Allen-Zhu, Sébastien Bubeck, Yuanzhi Li
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits. ICML (2018)
Zeyuan Allen-Zhu
How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD. NeurIPS (2018)
Chi Jin, Zeyuan Allen-Zhu, Sébastien Bubeck, Michael I. Jordan
Is Q-Learning Provably Efficient? NeurIPS (2018)
Zeyuan Allen-Zhu, Yuanzhi Li
NEON2: Finding Local Minima via First-Order Oracles. NeurIPS (2018)
Zeyuan Allen-Zhu
Natasha 2: Faster Non-Convex Optimization Than SGD. NeurIPS (2018)
Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang
Near-Optimal Design of Experiments via Regret Minimization. ICML (2017)
Zeyuan Allen-Zhu, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson
Much Faster Algorithms for Matrix Scaling. FOCS (2017)
Zeyuan Allen-Zhu, Yuanzhi Li
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU. ICML (2017)
Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls. CoRR (2017)
Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang
Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approach. CoRR (2017)
Zeyuan Allen-Zhu
Natasha 2: Faster Non-Convex Optimization Than SGD. CoRR (2017)
Zeyuan Allen-Zhu, Yuanzhi Li
Faster Principal Component Regression and Stable Matrix Chebyshev Approximation. ICML (2017)
Zeyuan Allen-Zhu
Katyusha: The First Direct Acceleration of Stochastic Gradient Methods. J. Mach. Learn. Res. 18 (2017)
Zeyuan Allen-Zhu, Yuanzhi Li
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition. ICML (2017)
Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls. NIPS (2017)
Zeyuan Allen-Zhu, Yuanzhi Li
Neon2: Finding Local Minima via First-Order Oracles. CoRR (2017)
Zeyuan Allen-Zhu
Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter. ICML (2017)
Zeyuan Allen-Zhu, Yuanzhi Li
First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate. FOCS (2017)