← Back to all news
arXiv Machine Learning By Amirmohammad Farzaneh, Osvaldo Simeone

Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees

Read the original on arXiv Machine Learning →

The paper introduces a statistical framework for post‑training hyperparameter selection, emphasizing the learn‑then‑test (LTT) paradigm. It treats hyperparameter tuning as a multiple hypothesis testing problem over a candidate set, enabling the selection of hyperparameters that meet specified reliability constraints such as risk bounds or information‑theoretic limits. The framework provides finite‑sample control of error probabilities using p‑values, e‑values, and concentration inequalities derived from first principles.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 3

HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC

HyperMC is a multi‑fidelity hyperparameter tuning framework for stochastic gradient Markov chain Monte Carlo (SGMCMC) that combines Hyperband-style resource allocation with kernel Stein discrepancy (KSD) evaluation. It uses successive‑halving brackets to explore a continuous hyperparameter space while progressively refining promising configurations within a fixed computational budget. Robust HyperMC further introduces global grid initialization and elite‑guided local refinement to reduce sensitivity to random candidate generation and noisy evaluations, and theoretical analysis shows that the successive‑halving component selects a near‑optimal configuration with high probability under suitable conditions.

By Ming Tan, Xiyun Jiao
More like this →
arXiv Machine Learning
Jul 31

Towards Stability of Parameter-Free Optimization

arXiv:2405. 04376v4 Announce Type: replace Abstract: Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge.

By Yijiang Pang, Shuyang Yu, Bao Hoang, Jiayu Zhou
More like this →