26 papers
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…
Equilibrium with Internal Transfers
Mingyang Liu, Gabriele Farina, Asuman Ozdaglar
Nash equilibrium (NE) arises from selfish utility maximization, yet its social welfare can be arbitrarily far from optimal. Moreover, computing an NE is intractable in general. We…
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…
Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
Chanwoo Park, Ziyang Chen, Asuman Ozdaglar +1
Large language models (LLMs) are increasingly deployed as "agents" for decision-making (DM) in interactive and dynamic environments. Yet, since they were not originally designed fo…