Concepedia

Xiyu Zhai

XZ

Statistics

Publications

11

Citations

1.3K

H-Index

11

Active since

2017

Affiliations

Massachusetts Institute of Technology(Current)

Carnegie Mellon University

Peking University

Southern California University for Professional Studies

University of Southern California

Xiyu Zhai is an author at Massachusetts Institute of Technology specializing in engineering, machine learning, and computer science.

Top concepts

EngineeringMachine LearningComputer ScienceDeep LearningApproximation TheoryData ScienceFunctional AnalysisStatistical InferenceArtificial IntelligenceStatistics

Publications per year

2017–2020

11

Publications

11

Gradient Descent Provably Optimizes Over-parameterized Neural Networks

Simon S. Du, Xiyu Zhai, Barnabás Póczos et al. · arXiv (Cornell University) · 2018 · 418 citations · Full text

Model Optimization, Hyperparameter Estimation, Engineering +12

Gradient descent finds global minima of deep neural networks

Simon S. Du, Jason D. Lee, Haochuan Li et al. · 2019 · 417 citations

Artificial Intelligence, Model Optimization, Convolutional Neural Network +11

Gradient Descent Finds Global Minima of Deep Neural Networks

Simon S. Du, Jason D. Lee, Haochuan Li et al. · arXiv (Cornell University) · 2018 · 198 citations · Full text

Artificial Intelligence, Model Optimization, Convolutional Neural Network +11

On the Multiple Descent of Minimum-Norm Interpolants and Restricted\n Lower Isometry of Kernels

Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai · arXiv (Cornell University) · 2019 · 59 citations · Full text

Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints

Wenlong Mou, Liwei Wang, Xiyu Zhai et al. · arXiv (Cornell University) · 2017 · 54 citations · Full text

1–5 of 11