Xiao Wang

23 papers A* 10A 2Journal 11
YearRankTypeTitle / Venue / Authors
2025 A* conf
Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games.
ICML
Yi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang, Volkan Cevher
2025 J jnl
Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games.
CoRR
Yi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang, Volkan Cevher
2024 A conf
Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games.
UAI
Yi Feng, Ping Li, Ioannis Panageas, Xiao Wang
2024 J jnl
Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games.
CoRR
Yi Feng, Ping Li, Ioannis Panageas, Xiao Wang
2024 A* conf
Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg.
ICML
Yi Feng, Georgios Piliouras, Xiao Wang
2024 J jnl
Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg.
CoRR
Yi Feng, Georgios Piliouras, Xiao Wang
2023 A* conf
On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails.
NeurIPS
Yi Feng, Hu Fu, Qun Hu, Ping Li, Ioannis Panageas, Bo Peng, Xiao Wang
2023 J jnl
On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails.
CoRR
Yi Feng, Hu Fu, Qun Hu, Ping Li, Ioannis Panageas, Bo Peng, Xiao Wang
2023 J jnl
Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
CoRR
Ioannis Panageas, Stratis Skoulakis, Luca Viano, Xiao Wang, Volkan Cevher
2023 A* conf
Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
ICML
Ioannis Panageas, Stratis Skoulakis, Luca Viano, Xiao Wang, Volkan Cevher
2022 A* conf
Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always.
IJCAI
Yi Feng, Ioannis Panageas, Xiao Wang
2022 J jnl
Accelerated Multiplicative Weights Update Avoids Saddle Points almost always.
CoRR
Yi Feng, Ioannis Panageas, Xiao Wang
2022 A* conf
AdaGrad Avoids Saddle Points.
ICML
Kimon Antonakopoulos, Panayotis Mertikopoulos, Georgios Piliouras, Xiao Wang
2021 J jnl
Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics.
CoRR
Georgios Piliouras, Xiao Wang
2021 A conf
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes.
AISTATS
Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang
2020 J jnl
Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently.
CoRR
Ioannis Panageas, Stratis Skoulakis, Antonios Varvitsiotis, Xiao Wang
2020 A* conf
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem.
ICLR
Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang
2020 A* conf
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev.
NeurIPS
Xiao Wang, Qi Lei, Ioannis Panageas
2020 J jnl
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev.
CoRR
Xiao Wang, Qi Lei, Ioannis Panageas
2020 J jnl
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes.
CoRR
Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang
2019 J jnl
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem.
CoRR
Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang
2019 A* conf
First-order methods almost always avoid saddle points: The case of vanishing step-sizes.
NeurIPS
Ioannis Panageas, Georgios Piliouras, Xiao Wang
2019 A* conf
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always.
ICML
Ioannis Panageas, Georgios Piliouras, Xiao Wang