{"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/sparse-activations-as-conformal-predictors","title":"Sparse Activations as Conformal Predictors","arxiv_id":"2502.14773","date":"2025-02-20","proceeding":null,"authors":["Margarida M. Campos","João Calém","Sophia Sklaviadis","Mário A. T. Figueiredo","André F. T. Martins"],"abstract":"Conformal prediction is a distribution-free framework for uncertainty quantification that replaces point predictions with sets, offering marginal coverage guarantees (i.e., ensuring that the prediction sets contain the true label with a specified probability, in expectation). In this paper, we uncover a novel connection between conformal prediction and sparse softmax-like transformations, such as sparsemax and $\\gamma$-entmax (with $\\gamma > 1$), which may assign nonzero probability only to a subset of labels. We introduce new non-conformity scores for classification that make the calibration process correspond to the widely used temperature scaling method. At test time, applying these sparse transformations with the calibrated temperature leads to a support set (i.e., the set of labels with nonzero probability) that automatically inherits the coverage guarantees of conformal prediction. Through experiments on computer vision and text classification benchmarks, we demonstrate that the proposed method achieves competitive results in terms of coverage, efficiency, and adaptiveness compared to standard non-conformity scores based on softmax.","url_abs":"https://arxiv.org/abs/2502.14773v1","url_pdf":"https://arxiv.org/pdf/2502.14773v1.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":"sparse-activations-as-conformal-predictors","repo_url":"https://github.com/deep-spin/sparse-activations-cp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conformal-prediction","task_name":"Conformal Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"set","method_name":"SET"},{"method_slug":"sparsemax","method_name":"Sparsemax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.14773","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}