continual learning 1fine-tuning 1game theory 1kl-regularization 1model auditing 1reinforcement learning 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Keegan Harris, Brian W. Lee, Ian Waudby-Smith +3
The paper introduces a game‑theoretic framework for RL fine‑tuning that determines the KL regularization coefficient by treating the trade‑off between reward and deviation from a r…
cs.LG2026
Blackwell Approachability and Gradient Equilibrium are Equivalent
Brian W. Lee, Nika Haghtalab, Michael I. Jordan +1
Gradient equilibrium (GEQ) is a recently introduced online optimization framework that generalizes first-order stationarity from offline optimization and abstracts problems like on…
cs.LG2025
Panprediction: Optimal Predictions for Any Downstream Task and Loss
Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu +2
Supervised learning is classically formulated as training a model to minimize a fixed loss function over a fixed distribution, or task. However, an emerging paradigm instead views…