Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909346993012736 |
|---|---|
| author | Adachi, Masaki Hayakawa, Satoshi Jørgensen, Martin Wan, Xingchen Nguyen, Vu Oberhauser, Harald Osborne, Michael A. |
| author_facet | Adachi, Masaki Hayakawa, Satoshi Jørgensen, Martin Wan, Xingchen Nguyen, Vu Oberhauser, Harald Osborne, Michael A. |
| contents | Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off between cost and speed -- larger batches are more costly, smaller batches lead to slower wall-clock run-times -- and the trade-off may change over the run (larger batches are often preferable earlier). To address this trade-off, we propose a novel Probabilistic Numerics framework that adaptively changes batch sizes. By framing batch selection as a quadrature task, our integration-error-aware algorithm facilitates the automatic tuning of batch sizes to meet predefined quadrature precision objectives, akin to how typical optimizers terminate based on convergence thresholds. This approach obviates the necessity for exhaustive searches across all potential batch sizes. We also extend this to scenarios with constrained active learning and constrained optimization, interpreting constraint violations as reductions in the precision requirement, to subsequently adapt batch construction. Through extensive experiments, we demonstrate that our approach significantly enhances learning efficiency and flexibility in diverse Bayesian batch active learning and Bayesian optimization applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05843 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach Adachi, Masaki Hayakawa, Satoshi Jørgensen, Martin Wan, Xingchen Nguyen, Vu Oberhauser, Harald Osborne, Michael A. Machine Learning Artificial Intelligence Numerical Analysis Computation 62C10, 62F15 Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off between cost and speed -- larger batches are more costly, smaller batches lead to slower wall-clock run-times -- and the trade-off may change over the run (larger batches are often preferable earlier). To address this trade-off, we propose a novel Probabilistic Numerics framework that adaptively changes batch sizes. By framing batch selection as a quadrature task, our integration-error-aware algorithm facilitates the automatic tuning of batch sizes to meet predefined quadrature precision objectives, akin to how typical optimizers terminate based on convergence thresholds. This approach obviates the necessity for exhaustive searches across all potential batch sizes. We also extend this to scenarios with constrained active learning and constrained optimization, interpreting constraint violations as reductions in the precision requirement, to subsequently adapt batch construction. Through extensive experiments, we demonstrate that our approach significantly enhances learning efficiency and flexibility in diverse Bayesian batch active learning and Bayesian optimization applications. |
| title | Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach |
| topic | Machine Learning Artificial Intelligence Numerical Analysis Computation 62C10, 62F15 |
| url | https://arxiv.org/abs/2306.05843 |