English
Related papers

Related papers: Finite sample posterior concentration in high-dime…

200 papers

Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large. However, many BNN applications are concerned with the BNN…

Machine Learning · Statistics 2020-11-30 Jiri Hron , Yasaman Bahri , Roman Novak , Jeffrey Pennington , Jascha Sohl-Dickstein

Approximate Bayesian computation allows for statistical analysis in models with intractable likelihoods. In this paper we consider the asymptotic behaviour of the posterior distribution obtained by this method. We give general results on…

Methodology · Statistics 2018-05-09 David T. Frazier , Gael M. Martin , Christian P. Robert , Judith Rousseau

The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex. For computational reasons, researchers approximate this posterior using inexpensive mini-batch methods such as mean-field variational…

Machine Learning · Computer Science 2021-04-30 Pavel Izmailov , Sharad Vikram , Matthew D. Hoffman , Andrew Gordon Wilson

Most of the consistency analyses of Bayesian procedures for variable selection in regression refer to pairwise consistency, that is, consistency of Bayes factors. However, variable selection in regression is carried out in a given class of…

Methodology · Statistics 2015-07-30 Elías Moreno , Javier Girón , George Casella

We develop scalable methods for producing conformal Bayesian predictive intervals with finite sample calibration guarantees. Bayesian posterior predictive distributions, $p(y \mid x)$, characterize subjective beliefs on outcomes of…

Methodology · Statistics 2021-06-15 Edwin Fong , Chris Holmes

Shrinkage prior are becoming more and more popular in Bayesian modeling for high dimensional sparse problems due to its computational efficiency. Recent works show that a polynomially decaying prior leads to satisfactory posterior…

Statistics Theory · Mathematics 2020-04-14 Qifan Song

We study frequentist properties of Bayesian and $L_0$ model selection, with a focus on (potentially non-linear) high-dimensional regression. We propose a construction to study how posterior probabilities and normalized $L_0$ criteria…

Statistics Theory · Mathematics 2021-10-07 David Rossell

We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian-process limits. Large-deviation theory provides explicit variational objectives-rate…

Machine Learning · Statistics 2026-02-27 Katerina Papagiannouli , Dario Trevisan , Giuseppe Pio Zitto

Uncovering genuine relationships between a response variable of interest and a large collection of covariates is a fundamental and practically important problem. In the context of Gaussian linear models, both the Bayesian and non-Bayesian…

Statistics Theory · Mathematics 2025-04-11 Jeyong Lee , Minwoo Chae , Ryan Martin

We study frequentist asymptotic properties of Bayesian procedures for high-dimensional Gaussian sparse regression when unknown nuisance parameters are involved. Nuisance parameters can be finite-, high-, or infinite-dimensional. A mixture…

Statistics Theory · Mathematics 2021-02-18 Seonghyun Jeong , Subhashis Ghosal

We consider the classification problem of a high-dimensional mixture of two Gaussians with general covariance matrices. Using the replica method from statistical physics, we investigate the asymptotic behavior of a general class of…

Machine Learning · Statistics 2024-10-29 Hanwen Huang , Peng Zeng

In this paper, we consider high-dimensional Gaussian graphical models where the true underlying graph is decomposable. A hierarchical $G$-Wishart prior is proposed to conduct a Bayesian inference for the precision matrix and its graph…

Statistics Theory · Mathematics 2021-02-18 Kyoungjae Lee , Xuan Cao

Solving ill-posed inverse problems by Bayesian inference has recently attracted considerable attention. Compared to deterministic approaches, the probabilistic representation of the solution by the posterior distribution can be exploited to…

Numerical Analysis · Mathematics 2016-11-03 Felix Lucka

We consider generic optimal Bayesian inference, namely, models of signal reconstruction where the posterior distribution and all hyperparameters are known. Under a standard assumption on the concentration of the free energy, we show how…

Probability · Mathematics 2022-07-19 Jean Barbier , Dmitry Panchenko

We consider heteroscedastic nonparametric regression models, when both the mean function and variance function are unknown and to be estimated with nonparametric approaches. We derive convergence rates of posterior distributions for this…

Statistics Theory · Mathematics 2010-10-07 Yuao Hu

We consider inference in the scalar diffusion model $dX_t=b(X_t)dt+\sigma(X_t)dW_t$ with discrete data $(X_{j\Delta_n})_{0\leq j \leq n}$, $n\to \infty,~\Delta_n\to 0$ and periodic coefficients. For $\sigma$ given, we prove a general…

Statistics Theory · Mathematics 2018-08-24 Kweku Abraham

We study the rate of convergence of posterior distributions in density estimation problems for log-densities in periodic Sobolev classes characterized by a smoothness parameter p. The posterior expected density provides a nonparametric…

Statistics Theory · Mathematics 2009-09-29 Catia Scricciolo

There is a rich literature proposing methods and establishing asymptotic properties of Bayesian variable selection methods for parametric models, with a particular focus on the normal linear regression model and an increasing emphasis on…

Statistics Theory · Mathematics 2011-08-16 Suprateek Kundu , David B. Dunson

High dimensional statistics deals with the challenge of extracting structured information from complex model settings. Compared with the growing number of frequentist methodologies, there are rather few theoretically optimal Bayes methods…

Statistics Theory · Mathematics 2018-08-21 Chao Gao , Aad W. van der Vaart , Harrison H. Zhou

Bayesian inference allows machine learning models to express uncertainty. Current machine learning models use only a single learnable parameter combination when making predictions, and as a result are highly overconfident when their…

Machine Learning · Computer Science 2022-02-23 Andrew Wood , Moshik Hershcovitch , Daniel Waddington , Sarel Cohen , Peter Chin
‹ Prev 1 3 4 5 6 7 10 Next ›