no code implementations • 19 Jan 2023 • Alice L'Huillier, Luke Travis, Ismaël Castillo, Kolyan Ray
We establish a general Bernstein--von Mises theorem for approximately linear semiparametric functionals of fractional posterior distributions based on nonparametric priors.
no code implementations • 16 May 2022 • Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
We rigorously prove that deep Gaussian process priors can outperform Gaussian process priors if the target function has a compositional structure.
1 code implementation • 19 Dec 2021 • Michael Komodromos, Eric Aboagye, Marina Evangelou, Sarah Filippi, Kolyan Ray
Few Bayesian methods for analyzing high-dimensional sparse survival data provide scalable variable selection, effect estimation and uncertainty quantification.
no code implementations • 22 Dec 2020 • Matteo Giordano, Kolyan Ray
We study nonparametric Bayesian models for reversible multi-dimensional diffusions with periodic drift.
Bayesian Inference Statistics Theory Numerical Analysis Numerical Analysis Probability Statistics Theory
no code implementations • NeurIPS 2020 • Kolyan Ray, Botond Szabo, Gabriel Clara
Variational Bayes (VB) is a popular scalable alternative to Markov chain Monte Carlo for Bayesian inference.
1 code implementation • NeurIPS 2019 • Kolyan Ray, Botond Szabo
Bayesian approaches have become increasingly popular in causal inference problems due to their conceptual simplicity, excellent performance and in-built uncertainty quantification ('posterior credible sets').
no code implementations • 15 Apr 2019 • Kolyan Ray, Botond Szabo
We study a mean-field spike and slab variational Bayes (VB) approximation to Bayesian model selection priors in sparse high-dimensional linear regression.