The Sample Complexity of Multiple Change Point Identification under Bandit Feedback

arXiv:2605.13252 · stat.ML, cs.LG, math.ST, stat.TH · Submitted 2026-05-13 · Read on arXiv

stat.ML, cs.LG, math.ST, stat.TH

Submitted: 2026-05-13

Updated: 2026-10-21

Comments: Accepted at NeurIPS 2026. 43 pages. v2: camera-ready version (extended related work, refined comparison with MCPI, corrected Lemma 1/Lemma 4 statements, code release)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Sample Complexity — 2× in this paper · explained in 20 episodes
• Adaptive Algorithm — 1× in this paper · explained in 1 episode

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing