Uncertainty quantification for the horseshoe (with discussion)

S van der Pas, B Szabó, A van der Vaart - 2017 - projecteuclid.org
Uncertainty Quantification for the Horseshoe (with Discussion) Page 1 Bayesian Analysis (2017)
12, Number 4, pp. 1221–1274 Uncertainty Quantification for the Horseshoe (with Discussion) …

Variational Gaussian processes for linear inverse problems

T Randrianarisoa, B Szabo - Advances in Neural …, 2023 - proceedings.neurips.cc
By now Bayesian methods are routinely used in practice for solving inverse problems. In
inverse problems the parameter or signal of interest is observed only indirectly, as an image …

[PDF][PDF] Bayesian nonparametric statistics, St-Flour lecture notes

IÃĢ Castillo - arxiv preprint arxiv:2402.16422, 2024 - arxiv.org
arxiv:2402.16422v1 [math.ST] 26 Feb 2024 Page 1 Bay!ian nonparamet"c #at$tics St-Flour
lecture notes Ismaël Castillo arxiv:2402.16422v1 [math.ST] 26 Feb 2024 Page 2 2 Principe. Si …

A review of uncertainty quantification for density estimation

S McDonald, D Campbell - 2021 - projecteuclid.org
A review of uncertainty quantification for density estimation Page 1 Statistics Surveys Vol. 15
(2021) 1–71 ISSN: 1935-7516 https://doi.org/10.1214/21-SS130 A review of uncertainty …

Needles and straw in a haystack: robust confidence for possibly sparse sequences

E Belitser, N Nurushev - 2020 - projecteuclid.org
Needles and straw in a haystack: Robust confidence for possibly sparse sequences Page 1
Bernoulli 26(1), 2020, 191–225 https://doi.org/10.3150/19-BEJ1122 Needles and straw in a …

Uncertainty quantification for sparse spectral variational approximations in Gaussian process regression

D Nieman, B Szabo, H van Zanten - Electronic Journal of Statistics, 2023 - projecteuclid.org
We investigate the frequentist guarantees of the variational sparse Gaussian process
regression model. In the theoretical analysis, we focus on the variational approach with …

Spike and slab empirical Bayes sparse credible sets

I Castillo, B Szabó - 2020 - projecteuclid.org
Spike and slab empirical Bayes sparse credible sets Page 1 Bernoulli 26(1), 2020, 127–158
https://doi.org/10.3150/19-BEJ1119 Spike and slab empirical Bayes sparse credible sets …

Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?

A Hadji, B Szabó - SIAM/ASA Journal on Uncertainty Quantification, 2021 - SIAM
We investigate the frequentist coverage properties of credible sets resulting from Gaussian
process priors with squared exponential covariance kernel. First, we show that by selecting …

Statistical guarantees for stochastic Metropolis-Hastings

S Bieringer, G Kasieczka, MF Steffen… - arxiv preprint arxiv …, 2023 - arxiv.org
A Metropolis-Hastings step is widely used for gradient-based Markov chain Monte Carlo
methods in uncertainty quantification. By calculating acceptance probabilities on batches, a …

Bayesian dyadic trees and histograms for regression

S Van Der Pas, V Ročková - Advances in Neural …, 2017 - proceedings.neurips.cc
Many machine learning tools for regression are based on recursive partitioning of the
covariate space into smaller regions, where the regression function can be estimated locally …