{"ID":2875887,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.01397","arxiv_id":"2509.01397","title":"Double Descent and Overparameterization in Particle Physics Data","abstract":"Recently, the benefit of heavily overparameterized models has been observed in machine learning tasks: models with enough capacity to easily cross the \\emph{interpolation threshold} improve in generalization error compared to the classical bias-variance tradeoff regime. We demonstrate this behavior for the first time in particle physics data and explore when and where `double descent' appears and under which circumstances overparameterization results in a performance gain.","short_abstract":"Recently, the benefit of heavily overparameterized models has been observed in machine learning tasks: models with enough capacity to easily cross the \\emph{interpolation threshold} improve in generalization error compared to the classical bias-variance tradeoff regime. We demonstrate this behavior for the first time i...","url_abs":"https://arxiv.org/abs/2509.01397","url_pdf":"https://arxiv.org/pdf/2509.01397v1","authors":"[\"Matthias Vigl\",\"Lukas Heinrich\"]","published":"2025-09-01T11:45:24Z","proceeding":"hep-ex","tasks":"[\"hep-ex\",\"cs.LG\",\"hep-ph\",\"physics.data-an\"]","methods":"[]","has_code":false}