Zhiyuan Li(李志远)

Ph.D

Computer Science Department, Princeton University

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

My research interest lies in the interface of theoretical computer science and machine learning.
Awards
Microsoft Research PhD Fellowship, 2020
The William G. Bowen Merit Fellowship, Princeton Univeristy, 2017

Papers17 papers

Sort

By YearBy Citation

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Sanjeev Arora,Simon S. Du,Zhiyuan Li,Ruslan Salakhutdinov,Ruosong Wang,Dingli Yu

ICLR, (2020)

Cited by14EIBibtex

Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets

Zhiyuan Li,Yi Zhang,Sanjeev Arora

Bibtex

Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate

Zhiyuan Li,Kaifeng Lyu,Sanjeev Arora

NeurIPS, (2020)

EIBibtex

An Exponential Learning Rate Schedule for Deep Learning

Zhiyuan Li,Sanjeev Arora

ICLR, (2020)

Cited by3EIBibtex

Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee

Wei Hu,Zhiyuan Li,Dingli Yu

ICLR, (2020)

EIBibtex

Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning

Zhiyuan Li, Yuping Luo,Kaifeng Lyu

Bibtex

Theoretical Analysis of Auto Rate-Tuning by Batch Normalization

Sanjeev Arora,Zhiyuan Li,Kaifeng Lyu

international conference on learning representations, (2019)

Cited by21EIBibtex

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Sanjeev Arora,Simon S. Du,Wei Hu,Zhiyuan Li,Ruosong Wang

International Conference on Machine Learning, (2019): 322-332

Cited by171EIBibtex

On Exact Computation with an Infinitely Wide Neural Net

Sanjeev Arora,Simon S. Du,Wei Hu,Zhiyuan Li,Ruslan Salakhutdinov,Ruosong Wang

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 8139-8148

Cited by133EIBibtex

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Rohith Kuditipudi,Xiang Wang, Holden Lee,Yi Zhang,Zhiyuan Li,Wei Hu,Sanjeev Arora,Rong Ge

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 14574-14583

Cited by4EIBibtex

Understanding Generalization of Deep Neural Networks Trained with Noisy Labels

Wei Hu,Zhiyuan Li,Dingli Yu

arXiv: Learning, (2019)

EIBibtex

Online Improper Learning with an Approximation Oracle

Elad Hazan,Wei Hu,Yuanzhi Li,Zhiyuan Li

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 5652-5660

Cited by1EIBibtex

Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

Behnam Neyshabur,Zhiyuan Li,Srinadh Bhojanapalli,Yann LeCun,Nathan Srebro

arXiv: Learning, (2018)

Cited by187EIBibtex

Stability of Generalized Two-sided Markets with Transaction Thresholds

Zhiyuan Li, Yicheng Liu,Pingzhong Tang,Tingting Xu,Wei Zhan

AAMAS, pp.290-298, (2017)

Cited by5EIBibtex

Learning in Games: Robustness of Fast Convergence

Dylan J. Foster,Zhiyuan Li,Thodoris Lykouris,Karthik Sridharan,Eva Tardos

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), (2016)

Bibtex

Learning in Games: Robustness of Fast Convergence

Dylan J. Foster,Zhiyuan Li,Thodoris Lykouris,Karthik Sridharan,Éva Tardos

neural information processing systems, pp.4727-4735, (2016)

Cited by52EIBibtex

Solving Marginal MAP Problems with NP Oracles and Parity Constraints

Yexiang Xue,Zhiyuan Li,Stefano Ermon,Carla P. Gomes,Bart Selman

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), (2016)

Cited by11EIBibtex

View All

Base Info Papers Patents Projects