{"ID":2848620,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25569","arxiv_id":"2510.25569","title":"A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes","abstract":"PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on the expected risk of a randomly sampled hypothesis. This requires stochastic predictions at test time, making PAC-Bayes unusable in many practical situations where a single deterministic hypothesis must be deployed. We propose a unified framework to extract guarantees holding for a single hypothesis from stochastic PAC-Bayesian guarantees. We present a general oracle bound and derive from it a numerical bound and a specialization to majority vote. We empirically show that our approach consistently outperforms popular baselines (by up to a factor of 2) when it comes to generalization bounds on deterministic classifiers.","short_abstract":"PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on the expected risk of a randomly sampled hypothesis. This requires stochastic predictions at test time,...","url_abs":"https://arxiv.org/abs/2510.25569","url_pdf":"https://arxiv.org/pdf/2510.25569v1","authors":"[\"Benjamin Leblanc\",\"Pascal Germain\"]","published":"2025-10-29T14:38:35Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}