AI RESEARCH
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
arXiv CS.LG
•
ArXi:2605.09337v1 Announce Type: new We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achieves robustness through sign-based updates along carefully designed directions and mitigates the resulting bias via a two-timescale mechanism. It admits both first-order and zeroth-order implementations and enables fully asynchronous execution without requiring a private reference dataset at the server.