{"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/learning-against-distributional-uncertainty","title":"Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity","arxiv_id":"2301.13565","date":"2023-01-31","proceeding":null,"authors":["Shixiong Wang","Haowei Wang","Xinke Li","Jean Honorio"],"abstract":"Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distributionally robust optimization (DRO), and regularization. However, three issues have to be raised: 1) the prior distribution in the Bayesian method and the regularizer in the regularization method are difficult to specify; 2) the DRO method tends to be overly conservative; 3) all the three methods are biased estimators of the true optimal cost. This paper studies a new framework that unifies the three approaches and addresses the three challenges above. The asymptotic properties (e.g., consistencies and asymptotic normalities), non-asymptotic properties (e.g., generalization bounds and unbiasedness), and solution methods of the proposed model are studied. The new model reveals the trade-off between the robustness to the unseen data and the specificity to the training data. Experiments on various real-world tasks validate the superiority of the proposed learning framework.","url_abs":"https://arxiv.org/abs/2301.13565v2","url_pdf":"https://arxiv.org/pdf/2301.13565v2.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":"learning-against-distributional-uncertainty","repo_url":"https://github.com/spratm-asleaf/robustness-specificity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.13565","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}