{"paper":{"title":"A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gautam Dasarathy, John Kevin Cava, Lalitha Sankar, Mario Diaz, Peter Kairouz, Tyler Sypherd","submitted_at":"2019-06-05T21:16:48Z","abstract_excerpt":"We introduce a tunable loss function called $\\alpha$-loss, parameterized by $\\alpha \\in (0,\\infty]$, which interpolates between the exponential loss ($\\alpha = 1/2$), the log-loss ($\\alpha = 1$), and the 0-1 loss ($\\alpha = \\infty$), for the machine learning setting of classification. Theoretically, we illustrate a fundamental connection between $\\alpha$-loss and Arimoto conditional entropy, verify the classification-calibration of $\\alpha$-loss in order to demonstrate asymptotic optimality via Rademacher complexity generalization techniques, and build-upon a notion called strictly local quasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02314","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.02314/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}