Sotabase

Career

· Postdoctoral Researcher, Simons Institute for the Theory of Computing, UC Berkeley2022–2024
· Assistant Professor, University of Wisconsin-Madison2022–
· PhD Student, Columbia University2016–2022
· TA for Graduate Courses, Columbia University2016–2018
· Undergraduate Studies, National Technical University of Athens (NTUA)

Publications (33)

No-regret learning and mixed Nash equilibria: They do not mix
Neural Information Processing Systems · 2020
93
cited
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
Neural Information Processing Systems · 2019
44
cited
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
Annual Conference Computational Learning Theory · 2021
42
cited
Efficiently avoiding saddle points with zero order methods: No gradients required
Neural Information Processing Systems · 2019
35
cited
On the Approximation Power of Two-Layer Networks of Random ReLUs
Annual Conference Computational Learning Theory · 2021
29
cited
Contracting with a Learning Agent
Neural Information Processing Systems · 2024
26
cited
Optimal Private Median Estimation under Minimal Distributional Assumptions
Neural Information Processing Systems · 2020
24
cited
On the convergence of policy gradient methods to Nash equilibria in general stochastic games
Neural Information Processing Systems · 2022
23
cited
First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces
Neural Information Processing Systems · 2022
22
cited
Smoothed complexity of local max-cut and binary max-CSP
Symposium on the Theory of Computing · 2019
21
cited
The convergence rate of regularized learning in games: From bandits and uncertainty to optimism and beyond
Neural Information Processing Systems · 2021
18
cited
Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent
Neural Information Processing Systems · 2021
15
cited
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
International Conference on Learning Representations · 2022
13
cited
The Computational Complexity of Multi-player Concave Games and Kakutani Fixed Points
ACM Conference on Economics and Computation · 2022
11
cited
Algorithms and Complexity for Computing Nash Equilibria in Adversarial Team Games
ACM Conference on Economics and Computation · 2023
9
cited
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
International Conference on Artificial Intelligence and Statistics · 2023
7
cited
Exploiting hidden structures in non-convex games for convergence to Nash equilibrium
Neural Information Processing Systems · 2023
6
cited
Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals
Annual Conference Computational Learning Theory · 2022
6
cited
Towards convergence to Nash equilibria in two-team zero-sum games
International Conference on Learning Representations · 2021
6
cited
A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games
Quantum · 2023
5
cited
Sotabase