{"ID":2826436,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19913","arxiv_id":"2512.19913","title":"Quasiprobabilistic Density Ratio Estimation with a Reverse Engineered Classification Loss Function","abstract":"We consider a generalization of the classifier-based density-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative. The problem with most loss functions used for this task is that they implicitly define a relationship between the optimal classifier and the target quasiprobabilistic density ratio which is discontinuous or not surjective. We address these problems by introducing a convex loss function that is well-suited for both probabilistic and quasiprobabilistic density ratio estimation. To quantify performance, an extended version of the Sliced-Wasserstein distance is introduced which is compatible with quasiprobability distributions. We demonstrate our approach on a real-world example from particle physics, of di-Higgs production in association with jets via gluon-gluon fusion, and achieve state-of-the-art results.","short_abstract":"We consider a generalization of the classifier-based density-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative. The problem with most loss functions used for this task is that they implicitly define a relationship between the optimal classifier and the target quasiprobabi...","url_abs":"https://arxiv.org/abs/2512.19913","url_pdf":"https://arxiv.org/pdf/2512.19913v1","authors":"[\"Matthew Drnevich\",\"Stephen Jiggins\",\"Kyle Cranmer\"]","published":"2025-12-22T22:37:19Z","proceeding":"stat.ML","tasks":"[\"stat.ML\",\"cs.LG\",\"hep-ex\"]","methods":"[]","has_code":false}