Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets

B Dupuis, P Viallard, G Deligiannidis… - Journal of Machine …, 2024 - jmlr.org
We propose data-dependent uniform generalization bounds by approaching the problem
from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on “random …

Generalization bounds for heavy-tailed SDEs through the fractional Fokker-Planck equation

B Dupuis, U Şimşekli - arxiv preprint arxiv:2402.07723, 2024 - arxiv.org
Understanding the generalization properties of heavy-tailed stochastic optimization
algorithms has attracted increasing attention over the past years. While illuminating …

Understanding the Generalization Error of Markov algorithms through Poissonization

B Dupuis, M Haddouche, G Deligiannidis… - arxiv preprint arxiv …, 2025 - arxiv.org
Using continuous-time stochastic differential equation (SDE) proxies to stochastic
optimization algorithms has proven fruitful for understanding their generalization abilities. A …