Tutorial: Federated Optimization, Part III | Peter Richtarik

DeepSeekMath 7B: Open-Source Math Model Surpasses GPT-4 | Byte Goose AI posted on the topic | LinkedIn

GRPO Family: Group Relative Policy Optimization RL opt [TIC-GRPO, Scaf-GRPO, XRPO, GRPO-CARE, CPPO] | Byte Goose AI

A Proximal Point Algorithm For Log-Determinant Optimization With Group Lazzo Regularization

Black-box optimization of CT acquisition and reconstruction parameters: a reinforcement learning approach