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

• URL: http://arxiv.org/abs/2409.15844v1
• Date: Tue, 24 Sep 2024 08:14:26 GMT
• Title: Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
• Authors: Matteo Zecchin, Osvaldo Simeone,
• Abstract summary: We introduce adaptive learn-then-test (aLTT), which provides finite-sample statistical guarantees on the population risk of AI models. ALTT can reduce the number of testing rounds, making it well-suited for scenarios in which testing is costly or presents safety risks.
• Score: 35.88667386998423
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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 hyperparameter tuning for engineering systems, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.

Related papers

• ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance [18.055032898349438]
  Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution. We introduce ETAGE, a refined TTA method that integrates entropy minimization with gradient norms and PLPD. Our method prioritizes samples that are less likely to cause instability by combining high entropy with high gradient norms out of adaptation.
  arXiv  Detail & Related papers  (2024-09-14T01:25:52Z)
• Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization [36.14499894307206]
  This work introduces a variant of learn-then-test (LTT) that is designed to provide statistical guarantees on quantiles of a risk measure. We illustrate the practical advantages of this approach by applying the proposed algorithm to a radio access scheduling problem.
  arXiv  Detail & Related papers  (2024-07-24T15:30:12Z)
• Active Test-Time Adaptation: Theoretical Analyses and An Algorithm [51.84691955495693]
  Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. We propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.
  arXiv  Detail & Related papers  (2024-04-07T22:31:34Z)
• Test-Time Training for Speech [6.697702130929691]
  We introduce distribution-shifts to the test datasets of standard speech-classification tasks. We explore how Test-Time Training (TTT) can help adjust to the distribution-shift.
  arXiv  Detail & Related papers  (2023-09-19T21:06:22Z)
• Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning [73.75282761503581]
  We propose DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13%.
  arXiv  Detail & Related papers  (2023-08-11T09:36:31Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [143.14128737978342]
  Test-time adaptation, an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.