English

Non-partitioned e-detectors for nonparametric sequential change detection

Methodology 2026-07-30 v1 Statistics Theory Machine Learning

Abstract

We study the problem of sequential change detection over a general class of probability distributions (P\mathcal P), where both the pre-change and post-change distributions are unknown and belong to P\mathcal P. We do not assume a pre-specified partition of P\mathcal P into pre- and post-change families. We propose a general class of sequential change detectors obtained by aggregating point-null e-processes over possible changepoints and taking an infimum over candidate no-change distributions. The weights in the aggregation scheme determine whether they attain average run length (ARL) control and probability-of-false-alarm (PFA) control. Under suitable assumptions, we prove that our methods achieve first-order asymptotically optimal detection delay. Concrete examples include sub-Gaussian and bounded mean changes, Gaussian mean changes with unknown variance, as well as changes in Markov transition matrices.

Cite

@article{arxiv.2607.28322,
  title  = {Non-partitioned e-detectors for nonparametric sequential change detection},
  author = {Aytijhya Saha and Aaditya Ramdas},
  journal= {arXiv preprint arXiv:2607.28322},
  year   = {2026}
}