Panayotis Mertikopoulos

Leveraging Similarities in Multi-Armed Bandits COLT 2026 Tamed Langevin sampling under weaker conditions AISTATS 2025 The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations ICML 2025 The impact of uncertainty on regularized learning in games ICML 2025 Accelerated Regularized Learning in Finite N-Person Games NeurIPS 2024 A Geometric Decomposition of Finite Games: Convergence vs. Recurrence under Exponential Weights ICML 2024 No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests NeurIPS 2024 The Computational Complexity of Finding Second-Order Stationary Points ICML 2024 What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis ICML 2024 Exploiting hidden structures in non-convex games for convergence to Nash equilibrium NeurIPS 2023 Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games NeurIPS 2023 Riemannian stochastic optimization methods avoid strict saddle points NeurIPS 2023 The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games NeurIPS 2023 AdaGrad Avoids Saddle Points ICML 2022 Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources ALT 2022 Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism JMLR 2022 Nested Bandits ICML 2022 No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation NeurIPS 2022 On the convergence of policy gradient methods to Nash equilibria in general stochastic games NeurIPS 2022 The Dynamics of Riemannian Robbins-Monro Algorithms COLT 2022 UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees ICML 2022 Adaptive Extra-Gradient Methods for Min-Max Optimization and Games ICLR 2021 Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements NeurIPS 2021 Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium COLT 2021 Fast Routing under Uncertainty: Adaptive Learning in Congestion Games via Exponential Weights NeurIPS 2021 On the Rate of Convergence of Regularized Learning in Games: From Bandits and Uncertainty to Optimism and Beyond NeurIPS 2021 Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach ICML 2021 Sifting through the noise: Universal first-order methods for stochastic variational inequalities NeurIPS 2021 Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information COLT 2021 The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities COLT 2021 The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets ICML 2021 Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging ICML 2021 A new regret analysis for Adam-type algorithms ICML 2020 Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling NeurIPS 2020 Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games ICML 2020 Gradient-free Online Learning in Continuous Games with Delayed Rewards ICML 2020 No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix NeurIPS 2020 Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approach ICLR 2020 Online Non-Convex Optimization with Imperfect Feedback NeurIPS 2020 On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems NeurIPS 2020 An adaptive Mirror-Prox method for variational inequalities with singular operators NeurIPS 2019 Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints ICML 2019 On the convergence of single-call stochastic extra-gradient methods NeurIPS 2019 Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile ICLR 2019 Bandit Learning in Concave N-Person Games NeurIPS 2018 Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? ICML 2018 Learning in Games with Lossy Feedback NeurIPS 2018 Countering Feedback Delays in Multi-Agent Learning NeurIPS 2017 Learning with Bandit Feedback in Potential Games NeurIPS 2017 Stochastic Mirror Descent in Variationally Coherent Optimization Problems NeurIPS 2017