Zeyuan Allen-Zhu

发表

A Convergence Theory for Deep Learning via Over-Parameterization pdf

Yuanzhi Li, Zeyuan Allen-Zhu, Zhao Song, 2018, ICML.

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

Yuanzhi Li, Zeyuan Allen-Zhu, 2020, ArXiv.

Nearly-Linear Time Packing and Covering LP Solver with Faster Convergence Rate Than O(1/" 2 )

Zeyuan Allen-Zhu, Lorenzo Orecchia, Zeyuan Allen-Zhu, 2014, 1411.1124.

Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits pdf

Yuanzhi Li, Sébastien Bubeck, Zeyuan Allen-Zhu, 2018, ICML.

Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition pdf

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2016, ICML.

What Can ResNet Learn Efficiently, Going Beyond Kernels?

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2019, NeurIPS.

Nearly linear-time packing and covering LP solvers

Zeyuan Allen-Zhu, Lorenzo Orecchia, Zeyuan Allen-Zhu, 2014, Math. Program..

Three Steps to Make the Traffic Circle Go Round

Zeyuan Allen-Zhu, Tianyi Mao, Yichen Huang, 2009 .

Neon2: Finding Local Minima via First-Order Oracles

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2017, NeurIPS.

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

Yuanzhi Li, Yingyu Liang, Zeyuan Allen-Zhu, 2018, NeurIPS.

On the Convergence Rate of Training Recurrent Neural Networks

Yuanzhi Li, Zeyuan Allen-Zhu, Zhao Song, 2018, NeurIPS.

Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2017, ICML.

Byzantine Stochastic Gradient Descent

Dan Alistarh, Zeyuan Allen-Zhu, Jerry Li, 2018, NeurIPS.

Using Optimization to Solve Positive LPs Faster in Parallel

Zeyuan Allen-Zhu, Lorenzo Orecchia, 2014 .

Mechanism design with approximate types

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2012 .

Near-optimal discrete optimization for experimental design: a regret minimization approach

Yuanzhi Li, Aarti Singh, Yining Wang, 2017, Mathematical Programming.

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

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2016, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

Much Faster Algorithms for Matrix Scaling

Avi Wigderson, Yuanzhi Li, Zeyuan Allen-Zhu, 2017, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

Novel frameworks for auctions and optimization

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2015 .

Can SGD Learn Recurrent Neural Networks with Provable Generalization?

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2019, NeurIPS.

Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing

Avi Wigderson, Yuanzhi Li, Ankit Garg, 2018, STOC.

Byzantine-Resilient Non-Convex Stochastic Gradient Descent pdf

Dan Alistarh, Zeyuan Allen-Zhu, Jerry Li, 2020, ICLR.

The Lingering of Gradients: How to Reuse Gradients Over Time

David Simchi-Levi, Zeyuan Allen-Zhu, Xinshang Wang, 2019, NeurIPS.

Is Q-learning Provably Efficient?

Michael I. Jordan, Sébastien Bubeck, Chi Jin, 2018, NeurIPS.

Natasha 2: Faster Non-Convex Optimization Than SGD

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2017, NeurIPS.

Katyusha: the first direct acceleration of stochastic gradient methods

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2016, J. Mach. Learn. Res..

Feature Purification: How Adversarial Training Performs Robust Deep Learning pdf

Yuanzhi Li, Zeyuan Allen-Zhu, 2020, ArXiv.

Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls

Yuanzhi Li, Elad Hazan, Zeyuan Allen-Zhu, 2017, NIPS.

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

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2018, NeurIPS.

Faster Principal Component Regression and Stable Matrix Chebyshev Approximation

Yuanzhi Li, Zeyuan Allen-Zhu, 2017, ICML.

How To Make the Gradients Small Stochastically pdf

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2018, NIPS 2018.

Linear Coupling of Gradient and Mirror Descent: A Novel, Simple Interpretation of Nesterov's Accelerated Method

Zeyuan Allen-Zhu, Lorenzo Orecchia, Zeyuan Allen-Zhu, 2014 .

Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2018, ICML.

Survey & Experiment: Towards the Learning Accuracy

Zeyuan Allen-Zhu, Zeyuan Allen-Zhu, 2010 .

Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU

Yuanzhi Li, Zeyuan Allen-Zhu, Yuanzhi Li, 2017, ICML.

Near-Optimal Design of Experiments via Regret Minimization

Yuanzhi Li, Yining Wang, Zeyuan Allen-Zhu, 2017, ICML.

Sparse sign-consistent Johnson–Lindenstrauss matrices: Compression with neuroscience-based constraints

Nir Shavit, Silvio Micali, Zeyuan Allen-Zhu, 2014, Proceedings of the National Academy of Sciences.

Backward Feature Correction: How Deep Learning Performs Deep Learning pdf

Yuanzhi Li, Zeyuan Allen-Zhu, 2020, ArXiv.

Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions pdf

Zeyuan Allen-Zhu, Yuanzhi Li, Yuanzhi Li, 2021, ArXiv.

LoRA: Low-Rank Adaptation of Large Language Models pdf

Yelong Shen, Zeyuan Allen-Zhu, Phillip Wallis, 2021, ICLR.

Mechanism Design With Approximate Player Types

Silvio Micali, Zeyuan Allen-Zhu, Alessandro Chiesa, 2011 .