7 papers
The Complexity of Nash Equilibrium in Network Congestion and Coordination Games
Ioannis Anagnostides, Ioannis Panageas, Jingming Yan
We show that computing a Nash equilibrium is CLS-complete for linear network congestion and network coordination games. As a result, finding a KKT point of a bilinear polynomial is…
Finding a Positive Index Nash Equilibrium is PPADS-Complete
Andreas Kontogiannis, Ioannis Panageas, Vasilis Pollatos +1
Every nondegenerate bimatrix game has a Nash equilibrium of Shapley index +1, since all equilibria are isolated, have index +1 or -1, and their indices sum to +1. We prove that the…
The Computational Complexity of Team Zero-Sum Games
Ioannis Anagnostides, Ioannis Panageas, Tuomas Sandholm +1
A celebrated consequence of the minimax theorem is that two-player zero-sum games admit a tractable equilibrium characterization. In many central applications, however, each side c…
On the Computational Complexity of Performative Prediction
Ioannis Anagnostides, Rohan Chauhan, Ioannis Panageas +2
Performative prediction captures the phenomenon where deploying a predictive model shifts the underlying data distribution. While simple retraining dynamics are known to converge l…
The Complexity of Finding Local Optima in Contrastive Learning
Jingming Yan, Yiyuan Luo, Vaggos Chatziafratis +3
Contrastive learning is a powerful technique for discovering meaningful data representations by optimizing objectives based on , often given as a…
The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
Ioannis Anagnostides, Ioannis Panageas, Tuomas Sandholm +1
We consider the problem of computing stationary points in min-max optimization, with a particular focus on the special case of computing Nash equilibria in (two-)team zero-sum game…
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
Fivos Kalogiannis, Jingming Yan, Ioannis Panageas
We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite-ho…