Pith. sign in

REVIEW 3 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.15844 v2 pith:7W54XMZR submitted 2024-09-24 stat.ML cs.AIcs.ITcs.LGmath.ITstat.ME

Matteo Zecchin , Sangwoo Park , Osvaldo Simeone This is my paper · ORCID
classification stat.MLcs.AIcs.ITcs.LGmath.ITstat.ME
keywords altttestinglearn-then-testselectionadaptiveefficienthyperparameterrounds
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 (LTT) technique, which relies on conventional p-value-based multiple hypothesis testing (MHT), aLTT implements sequential data-dependent MHT with early termination by leveraging e-processes. As a result, aLTT can reduce the number of testing rounds, making it particularly well-suited for scenarios in which testing is costly or presents safety risks. Apart from maintaining statistical validity, in applications such as online policy selection for offline reinforcement learning and prompt engineering, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Black-Box Edge AI Model Selection with Conformal Latency and Accuracy Guarantees

    cs.IT 2025-06 reject novelty 6.0 of 10

    Combining conformal risk control with an order-statistic delay bound, the paper proposes fixed and channel-adaptive model selection for wireless edge inference that claims guaranteed loss and deadline violation probability.

  2. Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Prediction sets paired with max-min decisions are a sufficient statistic for value-at-risk optimizing agents, and the RAC algorithm builds such sets with distribution-free coverage.

  3. Ensuring Reliability via Hyperparameter Selection: Review and Advances

    cs.LG 2025-02 conditional novelty 2.0 of 10

    The paper reviews methods that cast hyperparameter selection as multiple hypothesis testing to deliver formal risk guarantees.

Pith tools