Generalization of Hamiltonian algorithms
Not on the map. Why?
Abstract (arXiv)
The paper proves generalization results for a class of stochastic learning algorithms. The method applies whenever the algorithm generates an absolutely continuous distribution relative to some a-priori measure and the Radon Nikodym derivative has subgaussian concentration. Applications are bounds for the Gibbs algorithm and randomizations of stable deterministic algorithms as well as PAC-Bayesian bounds with data-dependent priors.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 9 of its 30 references that are in the map. First posted on arXiv 23 May 2024.
Builds on
9 of 30 references.
References · 9
- 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
- 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
- 2021User-friendly introduction to PAC-Bayes boundscited by 234
- 2019A Primer on PAC-Bayesian Learningcited by 130
- 2020Tighter risk certificates for neural networkscited by 112
- 2017Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priorscited by 81
- 2020PAC-Bayes Analysis Beyond the Usual Boundscited by 63
- 2018PAC-Bayes bounds for stable algorithms with instance-dependent priorscited by 21
- 2019Distribution-Dependent Analysis of Gibbs-ERM Principlecited by 17
Built on by
Citing papers per year: 2025: 2.
2 papers.