AI RESEARCH

Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting

arXiv CS.LG

ArXi:2510.03839v2 Announce Type: replace We present a theoretical framework for M-FISHER, a method for sequential distribution shift detection and stable adaptation in streaming data. For detection, we construct an exponential martingale from non-conformity scores and apply Ville's inequality to obtain time-uniform guarantees on false alarm control, ensuring statistical validity at any stopping time.