Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Stratis Skoulakis

Stratis Skoulakis

Min-Max Optimization Made Simple: Approximating the Proximal Point Method via Contraction Maps

Jan 16, 2023
Volkan Cevher, Georgios Piliouras, Ryann Sim, Stratis Skoulakis

* To appear in SOSA23

Access Paper or Ask Questions

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Nov 03, 2022
Ali Kavis, Stratis Skoulakis, Kimon Antonakopoulos, Leello Tadesse Dadi, Volkan Cevher

Figure 1 for Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Figure 2 for Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Figure 3 for Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Figure 4 for Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

* 23 pages, 2 figures, accepted at NeurIPS 2022

Access Paper or Ask Questions

Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

Jul 18, 2022
Georgios Piliouras, Lillian Ratliff, Ryann Sim, Stratis Skoulakis

Figure 1 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

Figure 2 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

Figure 3 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

Figure 4 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

* To appear in SAGT 2022

Access Paper or Ask Questions

Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU

Dec 19, 2021
Georgios Piliouras, Ryann Sim, Stratis Skoulakis

Figure 1 for Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU

Figure 2 for Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU

Figure 3 for Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU

* Constant regret bound of CMWU improved to achieve logarithmic dependence on the number of actions; Fixed minor typos

Access Paper or Ask Questions

Online Learning in Periodic Zero-Sum Games

Nov 05, 2021
Tanner Fiez, Ryann Sim, Stratis Skoulakis, Georgios Piliouras, Lillian Ratliff

Figure 1 for Online Learning in Periodic Zero-Sum Games

Figure 2 for Online Learning in Periodic Zero-Sum Games

Figure 3 for Online Learning in Periodic Zero-Sum Games

Figure 4 for Online Learning in Periodic Zero-Sum Games

* To appear at NeurIPS 2021

Access Paper or Ask Questions

Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Dec 15, 2020
Stratis Skoulakis, Tanner Fiez, Ryann Sim, Georgios Piliouras, Lillian Ratliff

Figure 1 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Figure 2 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Figure 3 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Figure 4 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

* To appear in AAAI 2021

Access Paper or Ask Questions