arXiv:2509.01397v1 Announce Type: cross 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.
Original: https://arxiv.org/abs/2509.01397