paper-with-me

Papers

Variational Bayesian Last Layers

2024-04-17 · James Harrison, John Willes, Jasper Snoek

We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variational Bayesian last layer (VBLL) can be trained and evaluated with only quadratic complexity in last layer width, and is thus (nearly) computationally free to add to standard architectures. We experimentally investigate VBLLs, and show that they improve predictive accuracy, calibration, and out of distribution detection over baselines across both regression and classification. Finally, we investigate combining VBLL layers with variational Bayesian feature learning, yielding a lower variance collapsed variational inference method for Bayesian neural networks.

📄 PDF Abstract BibTeX arXiv:2404.11599

Code (2)

vectorinstitute/vbll 공식 구현 pytorch
lightning-uq-box/lightning-uq-box pytorch

Tasks

Out-of-Distribution DetectionVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Bayesian Optimization via Continual Variational Last Layer Training

2024-12-12 · Paul Brunzema, Mikkel Jordahn, John Willes, Sebastian Trimpe 외

Gaussian Processes (GPs) are widely seen as the state-of-the-art surrogate models for Bayesian optimization (BO) due to their ability to model uncertainty and their performance on tasks where correlations are easily capt…

Bayesian OptimizationGaussian Processes

Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks

2021-05-10 · Jie Ran, Rui Lin, Hayden K. H. So, Graziano Chesi 외

Elasticities in depth, width, kernel size and resolution have been explored in compressing deep neural networks (DNNs). Recognizing that the kernels in a convolutional neural network (CNN) are 4-way tensors, we further e…

Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling

2024-08-07 · Jian Xu, Zhiqi Lin, Shigui Li, Min Chen 외

Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last laye…

Computational EfficiencyOut-of-Distribution DetectionUncertainty Quantification

A Variational Bayesian Inference Theory of Elasticity and Its Mixed Probabilistic Finite Element Method for Inverse Deformation Solutions in Any Dimension

2024-10-10 · Chao Wang, Shaofan Li

In this work, we have developed a variational Bayesian inference theory of elasticity, which is accomplished by using a mixed Variational Bayesian inference Finite Element Method (VBI-FEM) that can be used to solve the i…

Bayesian Inference

Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems

2026-03-31 · David Gonzalez, Alba Muixi, Beatriz Moya, Elias Cueto arxiv

The increasingly wide use of deep machine learning techniques in computational mechanics has significantly accelerated simulations of problems that were considered unapproachable just a few years ago. However, in critica…

Graph Neural Network