Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

arXiv:2605.27991 · stat.ML, cs.LG · Submitted 2026-05-27 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-05-27

Updated: 2026-11-09

Code: https://github.com/MinhaoYaooo/GF-REML

Terminology

Sources

Related papers