all AI news
Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
Feb. 23, 2024, 5:43 a.m. | Masaki Adachi, Satoshi Hayakawa, Martin J{\o}rgensen, Xingchen Wan, Vu Nguyen, Harald Oberhauser, Michael A. Osborne
cs.LG updates on arXiv.org arxiv.org
Abstract: 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 …
abstract active learning arxiv cost cs.ai cs.lg cs.na dynamic experimentation math.na parallelization speed stat.co stat.ml trade trade-off type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
#13721 - Data Engineer - AI Model Testing
@ Qualitest | Miami, Florida, United States
Elasticsearch Administrator
@ ManTech | 201BF - Customer Site, Chantilly, VA