{"ID":2857774,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09877","arxiv_id":"2510.09877","title":"Batch Bayesian Active Learning with Partial Batch Label Sampling","abstract":"Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian-based active learning offers principled objectives with explainable intuition, including Expected Error Reduction (EER), Expected Predictive Information Gain (EPIG), and Bayesian Active Learning by Disagreements (BALD). A key challenge of such methods is the difficult scaling to large batch sizes, leading to either computational challenges (BatchBALD) or dramatic performance drops (top-$B$ selection). Here, using a particular formulation of Bayesian Decision Theory, we derive Partial Batch Label Sampling (ParBaLS) for the EPIG algorithm. We show experimentally for several datasets that ParBaLS EPIG gives superior performance for a fixed budget and Bayesian Logistic Regression on embeddings from large pre-trained models. Our code is available at https://github.com/ADDAPT-ML/ParBaLS.","short_abstract":"Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian-based active learning offers principled objectives with explainable intuition, including Expected Error Reduction (EER), Expected Predictive Information...","url_abs":"https://arxiv.org/abs/2510.09877","url_pdf":"https://arxiv.org/pdf/2510.09877v3","authors":"[\"Kangping Hu\",\"Stephen Mussmann\"]","published":"2025-10-10T21:28:42Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"stat.ML\"]","methods":"[]","has_code":false,"code_links":[{"ID":608481,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2857774,"paper_url":"https://arxiv.org/abs/2510.09877","paper_title":"Batch Bayesian Active Learning with Partial Batch Label Sampling","repo_url":"https://github.com/ADDAPT-ML/ParBaLS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}