An adaptive bandit algorithm for multiple change-point localization achieves non-asymptotic sample bounds jointly controlled by jump magnitudes and change-point spacing for any fixed δ and η.
Journal of machine learning research , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A kernel-copula embedding statistic equals zero exactly when causal dependence between X and Y is stable and is strictly positive otherwise, with a near-linear estimator and convergence rates provided.
citing papers explorer
-
The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
An adaptive bandit algorithm for multiple change-point localization achieves non-asymptotic sample bounds jointly controlled by jump magnitudes and change-point spacing for any fixed δ and η.