3 papers
math.ST2026
Leveraging tails for adaptation
Sergios Agapiou, Ismaël Castillo, Paul Egels
We consider contraction of Bayesian posterior distributions in nonparametric settings where coefficients of a function over a basis or dictionary are given priors with --exponen…
math.ST2026
Heavy-tailed and Horseshoe priors for regression and sparse Besov rates
Sergios Agapiou, Ismaël Castillo, Paul Egels
The large variety of functions encountered in nonparametric statistics, calls for methods that are flexible enough to achieve optimal or near-optimal performance over a wide variet…
stat.ML2025
Posterior and variational inference for deep neural networks with heavy-tailed weights
Ismaël Castillo, Paul Egels
We consider deep neural networks in a Bayesian framework with a prior distribution sampling the network weights at random. Following a recent idea of Agapiou and Castillo (2023), w…