paper-with-me

Papers

Early Stopping Based on Repeated Significance

2024-08-01 · Eric Bax, Arundhyoti Sarkar, Alex Shtoff

For a bucket test with a single criterion for success and a fixed number of samples or testing period, requiring a $p$-value less than a specified value of $\alpha$ for the success criterion produces statistical confidence at level $1 - \alpha$. For multiple criteria, a Bonferroni correction that partitions $\alpha$ among the criteria produces statistical confidence, at the cost of requiring lower $p$-values for each criterion. The same concept can be applied to decisions about early stopping, but that can lead to strict requirements for $p$-values. We show how to address that challenge by requiring criteria to be successful at multiple decision points.

📄 PDF Abstract BibTeX arXiv:2408.00908

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Don't Waste Your Time: Early Stopping Cross-Validation

2024-05-06 · Edward Bergman, Lennart Purucker, Frank Hutter

State-of-the-art automated machine learning systems for tabular data often employ cross-validation; ensuring that measured performances generalize to unseen data, or that subsequent ensembling does not overfit. However, …

Bayesian OptimizationModel Selection

Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

2026-05-27 · Minhao Yao, Ruoyu Wang, Xihong Lin, Lin Liu 외 arxiv

Gradient-flow optimization is usually viewed as an algorithmic procedure for minimizing empirical loss, with training duration selected by validation or heuristic early stopping rules. We develop a statistical inference …

Online Algorithms for Repeated Optimal Stopping: Balancing Baseline Guarantees and Regret

2025-11-06 · Tsubasa Harada, Yasushi Kawase, Hanna Sumita arxiv

We study the repeated optimal stopping problem, in which the same optimal stopping instance with an unknown distribution is solved repeatedly over $T$ rounds. We aim to simultaneously achieve strong per-round performance…

Continuous Monitoring via Repeated Significance

2024-08-05 · Eric Bax, Arundhyoti Sarkar, Alex Shtoff

Requiring statistical significance at multiple interim analyses to declare a statistically significant result for an AB test allows less stringent requirements for significance at each interim analysis. Repeated repeated…

Expanding on Repeated Consumer Search Using Multi-Armed Bandits and Secretaries

2020-12-22 · Tung Yu Marco Chan

We seek to take a different approach in deriving the optimal search policy for the repeated consumer search model found in Fishman and Rob (1995) with the main motivation of dropping the assumption of prior knowledge of …

Multi-Armed Bandits