Georgios Piliouras

Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play COLT 2025 Learning and steering game dynamics towards desirable outcomes L4DC 2025 Solving Zero-Sum Convex Markov Games ICML 2025 Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning ICML 2025 Re-evaluating Open-ended Evaluation of Large Language Models ICLR 2025 Scalable AI Safety via Doubly-Efficient Debate ICML 2024 Convergence of No-Swap-Regret Dynamics in Self-Play NIPS 2024 No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests NIPS 2024 Generative Adversarial Equilibrium Solvers ICLR 2024 Beating Price of Anarchy and Gradient Descent without Regret in Potential Games ICLR 2024 Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization ICLR 2024 NfgTransformer: Equivariant Representation Learning for Normal-form Games ICLR 2024 Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg ICML 2024 Alternation makes the adversary weaker in two-player games NIPS 2023 Exploiting hidden structures in non-convex games for convergence to Nash equilibrium NIPS 2023 The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium NIPS 2023 Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics IJCAI 2023 Alternating Mirror Descent for Constrained Min-Max Games NIPS 2022 AdaGrad Avoids Saddle Points ICML 2022 Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence NIPS 2022 Scalable Deep Reinforcement Learning Algorithms for Mean Field Games ICML 2022 Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update NIPS 2022 Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games ICLR 2022 The Evolution of Uncertainty of Learning in Games ICLR 2022 Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs ICLR 2022 Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality NIPS 2021 Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory AAAI 2021 Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games AAAI 2021 Learning in Matrix Games can be Arbitrarily Complex COLT 2021 Learning in Markets: Greed Leads to Chaos but Following the Price is Right IJCAI 2021 Follow-the-Regularized-Leader Routes to Chaos in Routing Games ICML 2021 Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence ICML 2021 Efficient Online Learning for Dynamic k-Clustering ICML 2021 From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization ICML 2021 Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent NIPS 2021 Online Learning in Periodic Zero-Sum Games NIPS 2021 Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent COLT 2020 From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics ICML 2020 No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix NIPS 2020 Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent NIPS 2020 Chaos, Extremism and Optimism: Volume Analysis of Learning in Games NIPS 2020 Smooth markets: A basic mechanism for organizing gradient-based learners ICLR 2020 The route to chaos in routing games: When is price of anarchy too optimistic? NIPS 2020 First-order methods almost always avoid saddle points: The case of vanishing step-sizes NIPS 2019 Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games COLT 2019 Efficiently avoiding saddle points with zero order methods: No gradients required NIPS 2019 Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes NIPS 2019 Multiagent Evaluation under Incomplete Information NIPS 2019 Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always ICML 2019 The Unusual Effectiveness of Averaging in GAN Training ICLR 2019 Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile ICLR 2019 Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games NIPS 2019 Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos NIPS 2017