Pith. sign in

20 30 40 50 60 70 80 90 100 log(1/ ) 500 1000 1500 2000 2500Stopping Time MCPI lower bound Figure

We again see that the average stopping time of MCPI is approximately parallel to the lower bound, supporting our theoretical results that MCPI is an asymptotically optimal Any-(N, δ) policy which is robust to an unknown number of additional · 2000

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

citation-role summary

baseline 1

citation-polarity summary

unclear 1

fields

stat.ML 1

years

2025 1

verdicts

CONDITIONAL 1

roles

baseline 1

polarities

unclear 1

representative citing papers

Fixed-Confidence Multiple Change Point Identification under Bandit Feedback

stat.ML · 2025-07-11 · conditional · novelty 6.0

For fixed-confidence multiple change point identification under bandit feedback, the paper derives instance-dependent lower bounds and an asymptotically optimal Track-and-Stop variant (MCPI) that samples near each jump in proportion to one over the jump size squared.

citing papers explorer

Showing 1 of 1 citing paper.

  • Fixed-Confidence Multiple Change Point Identification under Bandit Feedback stat.ML · 2025-07-11 · conditional · none · ref 1

    For fixed-confidence multiple change point identification under bandit feedback, the paper derives instance-dependent lower bounds and an asymptotically optimal Track-and-Stop variant (MCPI) that samples near each jump in proportion to one over the jump size squared.