paper-with-me

Papers

Asymptotic Properties for Bayesian Neural Network in Besov Space

2022-06-01 · Kyeongwon Lee, Jaeyong Lee

Neural networks have shown great predictive power when dealing with various unstructured data such as images and natural languages. The Bayesian neural network captures the uncertainty of prediction by putting a prior distribution for the parameter of the model and computing the posterior distribution. In this paper, we show that the Bayesian neural network using spike-and-slab prior has consistency with nearly minimax convergence rate when the true regression function is in the Besov space. Even when the smoothness of the regression function is unknown the same posterior convergence rate holds and thus the spike-and-slab prior is adaptive to the smoothness of the regression function. We also consider the shrinkage prior, which is more feasible than other priors, and show that it has the same convergence rate. In other words, we propose a practical Bayesian neural network with guaranteed asymptotic properties.

📄 PDF Abstract BibTeX arXiv:2206.00241

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Posterior Contraction of Lévy Adaptive B-spline Regression in Besov Spaces

2026-05-19 · Jeunghun Oh, Sewon Park, Jaeyong Lee arxiv

We investigate the asymptotic properties of the Lévy Adaptive B-spline (LABS) regression model, a Bayesian nonparametric method that incorporates B-spline kernels into the Lévy Adaptive Regression Kernel (LARK) model. LA…

Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces

2026-05-12 · Jeunghun Oh, Kyeongwon Lee, Jaeyong Lee, Lizhen Lin arxiv

We study posterior contraction rates for sparse Bayesian Kolmogorov-Arnold networks (KANs) over anisotropic Besov spaces, providing a statistical foundation of KANs from a Bayesian point of view. We show that sparse Baye…

On Estimation of $L_{r}$-Norms in Gaussian White Noise Models

2017-10-11 · Yanjun Han, Jiantao Jiao, Rajarshi Mukherjee

We provide a complete picture of asymptotically minimax estimation of $L_r$-norms (for any $r\ge 1$) of the mean in Gaussian white noise model over Nikolskii-Besov spaces. In this regard, we complement the work of Lepski…

Bayesian Learning via Q-Exponential Process

2022-10-14 · NeurIPS 2023 11 · Shuyi Li, Michael O'Connor, Shiwei Lan

Regularization is one of the most fundamental topics in optimization, statistics and machine learning. To get sparsity in estimating a parameter $u\in\mathbb{R}^d$, an $\ell_q$ penalty term, $\Vert u\Vert_q$, is usually …

Spatiotemporal Besov Priors for Bayesian Inverse Problems

2023-06-28 · Shiwei Lan, Mirjeta Pasha, Shuyi Li, Weining Shen

Fast development in science and technology has driven the need for proper statistical tools to capture special data features such as abrupt changes or sharp contrast. Many inverse problems in data science require spatiot…

CT ReconstructionDynamic ReconstructionGaussian ProcessesUncertainty Quantification