{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/active-bias-training-more-accurate-neural","title":"Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples","arxiv_id":"1704.07433","date":"2017-04-24","proceeding":"NeurIPS 2017 12","authors":["Haw-Shiuan Chang","Erik Learned-Miller","Andrew McCallum"],"abstract":"Self-paced learning and hard example mining re-weight training instances to\nimprove learning accuracy. This paper presents two improved alternatives based\non lightweight estimates of sample uncertainty in stochastic gradient descent\n(SGD): the variance in predicted probability of the correct class across\niterations of mini-batch SGD, and the proximity of the correct class\nprobability to the decision threshold. Extensive experimental results on six\ndatasets show that our methods reliably improve accuracy in various network\narchitectures, including additional gains on top of other popular training\ntechniques, such as residual learning, momentum, ADAM, batch normalization,\ndropout, and distillation.","url_abs":"http://arxiv.org/abs/1704.07433v4","url_pdf":"http://arxiv.org/pdf/1704.07433v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"active-bias-training-more-accurate-neural","repo_url":"https://github.com/zhangyuwangumass/Trajectory-Reweighted-Sampler","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.07433","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}