EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale.

arXiv:2609.10980v2 Announce Type: replace-cross Abstract: EGGROLL (Sarkar et al., 2026) makes evolution strategies (ES) practical for LLMs by replacing dense Gaussian weight perturbations with low-rank Gaussian products, often of rank one. This choice is compu