paper-with-me

Papers

A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties

2024-02-22 · David J. Schodt, Ryan Brown, Michael Merritt, Samuel Park, Delsin Menolascino, Mark A. Peot

Obtaining heteroscedastic predictive uncertainties from a Bayesian Neural Network (BNN) is vital to many applications. Often, heteroscedastic aleatoric uncertainties are learned as outputs of the BNN in addition to the predictive means, however doing so may necessitate adding more learnable parameters to the network. In this work, we demonstrate that both the heteroscedastic aleatoric and epistemic variance can be embedded into the variances of learned BNN parameters, improving predictive performance for lightweight networks. By complementing this approach with a moment propagation approach to inference, we introduce a relatively simple framework for sampling-free variational inference suitable for lightweight BNNs.

📄 PDF Abstract BibTeX arXiv:2402.14532

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Large-scale Heteroscedastic Regression via Gaussian Process

2018-11-03 · Haitao Liu, Yew-Soon Ong, Jianfei Cai

Heteroscedastic regression considering the varying noises among observations has many applications in the fields like machine learning and statistics. Here we focus on the heteroscedastic Gaussian process (HGP) regressio…

regressionVariational Inference

Deterministic Variational Inference for Robust Bayesian Neural Networks

2018-10-09 · ICLR 2019 5 · Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner 외

Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural network…

Variational Inference

Robust Variational Bayesian Point Set Registration

2019-10-01 · ICCV 2019 10 · Jie Zhou, Xinke Ma, Li Liang, Yang Yang 외

In this work, we propose a hierarchical Bayesian network based point set registration method to solve missing correspondences and various massive outliers. We construct this network first using the finite Student s t lat…

Variational Inference

Moment Matters: Mean and Variance Causal Graph Discovery from Heteroscedastic Observational Data

2026-02-27 · Yoichi Chikahara arxiv

Heteroscedasticity -- where the variance of a variable changes with other variables -- is pervasive in real data, and elucidating why it arises from the perspective of statistical moments is crucial in scientific knowled…

Uncertainty Quantification for Scientific Machine Learning using Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KAN)

2025-12-04 · Y. Sungtaek Ju arxiv

Kolmogorov-Arnold Networks have emerged as interpretable alternatives to traditional multi-layer perceptrons. However, standard implementations lack principled uncertainty quantification capabilities essential for many s…

Out-of-Distribution DetectionBayesian Inference