11 papers
Breaking Barrier in Quantum Zero-Sum Games: Generalizing Metric Subregularity for Spectraplexes
Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Pucheng Xiong
Quantum zero-sum games provide a framework for non-local games, quantum interactive proofs, and quantum machine learning, where players optimize a bilinear payoff over quantum stat…
Learning Safely Without Knowing the World:COMPASS-Hedge
Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis
Online learning algorithms often face a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed…
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis
We study adversarial multi-armed bandits with and without delayed feedback under a safety-aware goal: achieving minimax-optimal worst-case regret while keeping nearly constant regr…
No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis
We investigate the strategic surplus obtainable against a Follow-the-Regularized-Leader (FTRL) learner with constant step size in two-player zero-sum games played…
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
Konstantinos Emmanouilidis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Rene Vidal
From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min-max optimization or, more generally, as variational inequality proble…
Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics
Deep Patel, Emmanouil-Vasileios Vlatakis-Gkaragkounis
Many emerging applications - such as adversarial training, AI alignment, and robust optimization - can be framed as zero-sum games between neural nets, with von Neumann-Nash equili…