Xiao Wang

Affiliations:
  • Singapore University of Technology and Design, Singapore


According to our database1, Xiao Wang authored at least 11 papers between 2019 and 2023.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails.
CoRR, 2023

Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
Proceedings of the International Conference on Machine Learning, 2023

2022
Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

AdaGrad Avoids Saddle Points.
Proceedings of the International Conference on Machine Learning, 2022

2021
Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics.
CoRR, 2021

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently.
CoRR, 2020

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
First-order methods almost always avoid saddle points: The case of vanishing step-sizes.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always.
Proceedings of the 36th International Conference on Machine Learning, 2019


  Loading...