Zeyuan Allen-Zhu

Overview

Best Publications

• LoRA: Low-Rank Adaptation of Large Language Models.

  Edward J. Hu;Yelong Shen;Phillip Wallis;Zeyuan Allen-Zhu

  2371
  Citations

• A Convergence Theory for Deep Learning via Over-Parameterization

  Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  821
  Citations

• A Convergence Theory for Deep Learning via Over-Parameterization

  Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  616
  Citations

• Katyusha: The First Direct Acceleration of Stochastic Gradient Methods

  Zeyuan Allen-Zhu

  508
  Citations

• Is Q-learning Provably Efficient?

  Chi Jin;Zeyuan Allen-Zhu;Sebastien Bubeck;Michael I. Jordan

  462
  Citations

• Variance reduction for faster non-convex optimization

  Zeyuan Allen-Zhu;Elad Hazan

  342
  Citations

• A simple, combinatorial algorithm for solving SDD systems in nearly-linear time

  Jonathan A. Kelner;Lorenzo Orecchia;Aaron Sidford;Zeyuan Allen Zhu

  261
  Citations

• Natasha 2: Faster Non-Convex Optimization Than SGD

  Zeyuan Allen-Zhu

  220
  Citations

• Finding approximate local minima faster than gradient descent

  Naman Agarwal;Zeyuan Allen-Zhu;Brian Bullins;Elad Hazan

  211
  Citations

• Byzantine Stochastic Gradient Descent

  Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

  208
  Citations

• Asymptotically optimal strategy-proof mechanisms for two-facility games

  Pinyan Lu;Xiaorui Sun;Yajun Wang;Zeyuan Allen Zhu

  190
  Citations

• Improved SVRG for non-strongly-convex or sum-of-non-convex objectives

  Zeyuan Allen-Zhu;Yang Yuan

  177
  Citations

• Even faster accelerated coordinate descent using non-uniform sampling

  Zeyuan Allen-Zhu;Zheng Qu;Peter Richtárik;Yang Yuan

  166
  Citations

• Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

  Zeyuan Allen-Zhu;Yuanzhi Li;Yingyu Liang

  164
  Citations

• Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

  Zeyuan Allen-Zhu;Yuanzhi Li

  163
  Citations

• Variance Reduction for Faster Non-Convex Optimization

  Zeyuan Allen-Zhu;Elad Hazan

  157
  Citations

• On the Convergence Rate of Training Recurrent Neural Networks

  Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  134
  Citations

• What Can ResNet Learn Efficiently, Going Beyond Kernels?

  Zeyuan Allen-Zhu;Yuanzhi Li

  124
  Citations

• A novel click model and its applications to online advertising

  Zeyuan Allen Zhu;Weizhu Chen;Tom Minka;Chenguang Zhu

  124
  Citations

• Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

  Unknown

  119
  Citations

• Randomized accuracy-aware program transformations for efficient approximate computations

  Zeyuan Allen Zhu;Sasa Misailovic;Jonathan A. Kelner;Martin Rinard

  118
  Citations

• Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent

  Unknown

  118
  Citations

• NEON2: Finding Local Minima via First-Order Oracles

  Zeyuan Allen-Zhu;Yuanzhi Li

  111
  Citations

• A Local Algorithm for Finding Well-Connected Clusters

  Zeyuan Allen Zhu;Silvio Lattanzi;Vahab Mirrokni

  106
  Citations

• LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain

  Zeyuan Allen-Zhu;Yuanzhi Li

  105
  Citations

• Feature Purification: How Adversarial Training Performs Robust Deep Learning

  Zeyuan Allen-Zhu;Yuanzhi Li

  103
  Citations

• Much Faster Algorithms for Matrix Scaling

  Zeyuan Allen-Zhu;Yuanzhi Li;Rafael Oliveira;Avi Wigderson

  99
  Citations

• P-packSVM: Parallel Primal grAdient desCent Kernel SVM

  Zeyuan Allen Zhu;Weizhu Chen;Gang Wang;Chenguang Zhu

  97
  Citations

• First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate

  Zeyuan Allen-Zhu;Yuanzhi Li

  88
  Citations

• Backward Feature Correction: How Deep Learning Performs Deep Learning

  Zeyuan Allen-Zhu;Yuanzhi Li

  86
  Citations

• Byzantine Stochastic Gradient Descent

  Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

  73
  Citations

• How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD

  Zeyuan Allen-Zhu

  45
  Citations

• Even Faster SVD Decomposition Yet Without Agonizing Pain

  Zeyuan Allen Zhu;Yuanzhi Li

  7
  Citations