2 papers
cs.LG2026
Predictable GRPO: A Closed-Form Model of Training Dynamics
Rajat Ghosh, Datta Nimmaturi, Aryan Singhal +4
We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO upda…
cs.LG2026
Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models
Datta Nimmaturi, Vaishnavi Bhargava, Rajat Ghosh +2
Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To ad…