11 papers · 1 filter
Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex
Chanwoo Park, Asuman Ozdaglar
We revisit the regret loss framework introduced in Park et al. (2025), which uses decision-theoretic regret as a direct loss function for training models to make better decisions,…
Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis
Zaiwei Chen, Kaiqing Zhang, Eric Mazumdar +2
We present a finite-sample analysis of decentralized learning in two-player zero-sum matrix games and stochastic games, with a focus on best-response-based learning algorithms. In…
Regret Minimization with Adaptive Opponents in Repeated Games
Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu +1
In this paper, we study regret minimization in repeated games with \emph{adaptive} opponents who can respond based on histories of play. The standard metric of \emph{external regre…
Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
Gagik Magakyan, Amirhossein Reisizadeh, Chanwoo Park +2
Adaptability has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning met…
Online Learning and Equilibrium Computation with Ranking Feedback
Mingyang Liu, Yongshan Chen, Zhiyuan Fan +3
Online learning in arbitrary, and possibly adversarial, environments has been extensively studied in sequential decision-making, and it is closely connected to equilibrium computat…
Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
Runyu Zhang, Na Li, Asuman Ozdaglar +2
Risk sensitivity has become a central theme in reinforcement learning (RL), where convex risk measures and robust formulations provide principled ways to model preferences beyond e…