Yi Zhang

According to our database, Yi Zhang authored at least 16 papers between 2017 and 2022.

Collaborative distances:

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

2022

On Predicting Generalization using GANs.

Yi Zhang, Arushi Gupta, Nikunj Saunshi, Sanjeev Arora

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data.

Sanjeev Arora, Yi Zhang

CoRR, 2021

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

Zhiyuan Li, Yi Zhang, Sanjeev Arora

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

2020

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality.

Yi Zhang, Orestis Plevrakis, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora

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

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning.

Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora

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

Extreme Tensoring for Low-Memory Preconditioning.

Xinyi Chen, Naman Agarwal, Elad Hazan, Cyril Zhang, Yi Zhang

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets.

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

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

Efficient Full-Matrix Adaptive Regularization.

Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

The Case for Full-Matrix Adaptive Regularization.

Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang

CoRR, 2018

Spectral Filtering for General Linear Dynamical Systems.

Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Stronger Generalization Bounds for Deep Nets via a Compression Approach.

Sanjeev Arora, Rong Ge, Behnam Neyshabur, Yi Zhang

Proceedings of the 35th International Conference on Machine Learning, 2018

Do GANs learn the distribution? Some Theory and Empirics.

Sanjeev Arora, Andrej Risteski, Yi Zhang

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

Towards Provable Control for Unknown Linear Dynamical Systems.

Sanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

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

2017

Theoretical limitations of Encoder-Decoder GAN architectures.

Sanjeev Arora, Andrej Risteski, Yi Zhang

CoRR, 2017

Do GANs actually learn the distribution? An empirical study.

Sanjeev Arora, Yi Zhang

CoRR, 2017

Generalization and Equilibrium in Generative Adversarial Nets (GANs).

Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang

Proceedings of the 34th International Conference on Machine Learning, 2017