paper-with-me

Papers

Statistically Valid Hyperparameter Selection: From Tuning to Guarantees

2026-06-24 · Amirmohammad Farzaneh, Osvaldo Simeone arxiv

Hyperparameter selection is a critical step in the deployment of modern artificial intelligence systems, given the need to tune degrees of freedom such as inference-time parameters, implementation-level settings, and thresholds driving decision rules. Despite its practical importance, hyperparameter selection is typically performed using best-effort empirical methods such as grid search or Bayesian optimization, which provide no formal statistical guarantees on reliability or safety. This monograph presents a unified statistical framework for reliable hyperparameter selection, centered on the learn-then-test (LTT) paradigm, which formulates the problem as multiple hypothesis testing over a candidate set of hyperparameters. The framework enables the selection of hyperparameters that provably satisfy application-specific reliability requirements -- such as bounds on average risk, quantile risk, or information-theoretic constraints -- with explicit, finite-sample control of error probabilities. The supporting statistical machinery, namely p-values, e-values, and concentration inequalities, is developed from first principles in a dedicated appendix.

📄 PDF Abstract BibTeX arXiv:2606.25601

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection

2024-09-24 · Matteo Zecchin, Sangwoo Park, Osvaldo Simeone

We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models. Unlike the existing learn-then-test (L…

Prompt Engineeringvalid

A Unified Framework for Tuning Hyperparameters in Clustering Problems

2019-10-17 · Xinjie Fan, Yuguang Yue, Purnamrita Sarkar, Y. X. Rachel Wang

Selecting hyperparameters for unsupervised learning problems is challenging in general due to the lack of ground truth for validation. Despite the prevalence of this issue in statistics and machine learning, especially i…

ClusteringCommunity DetectionModel Selection

On hyperparameter tuning in general clustering problemsm

2020-01-01 · ICML 2020 1 · Xinjie Fan, Yuguang Yue, Purnamrita Sarkar, Y. X. Rachel Wang

Tuning hyperparameters for unsupervised learning problems is difficult in general due to the lack of ground truth for validation. However, the success of most clustering methods depends heavily on the correct choice of t…

ClusteringCommunity DetectionModel Selection

Statistically Valid Information Bottleneck via Multiple Hypothesis Testing

2024-09-11 · Amirmohammad Farzaneh, Osvaldo Simeone

The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, current approaches to solving the IB proble…

valid

Frequency-Based Hyperparameter Selection in Games

2026-01-26 · Aniket Sanyal, Baraah A. M. Sidahmed, Rebekka Burkholz, Tatjana Chavdarova arxiv

Learning in smooth games fundamentally differs from standard minimization due to rotational dynamics, which invalidate classical hyperparameter tuning strategies. Despite their practical importance, effective methods for…