paper-with-me

홈 › Papers

Do Bayesian Neural Networks Need To Be Fully Stochastic?

2022-11-11 · Mrinank Sharma, Sebastian Farquhar, Eric Nalisnick, Tom Rainforth

We investigate the benefit of treating all the parameters in a Bayesian neural network stochastically and find compelling theoretical and empirical evidence that this standard construction may be unnecessary. To this end, we prove that expressive predictive distributions require only small amounts of stochasticity. In particular, partially stochastic networks with only $n$ stochastic biases are universal probabilistic predictors for $n$-dimensional predictive problems. In empirical investigations, we find no systematic benefit of full stochasticity across four different inference modalities and eight datasets; partially stochastic networks can match and sometimes even outperform fully stochastic networks, despite their reduced memory costs.

📄 PDF Abstract BibTeX arXiv:2211.06291

Code (2)

MrinankSharma/do_bnns_need_to_be_fully_stochastic 공식 구현 jax
lightning-uq-box/lightning-uq-box pytorch

Similar Papers 제목 키워드 기반

A Tractable Fully Bayesian Method for the Stochastic Block Model

2016-02-06 · Kohei Hayashi, Takuya Konishi, Tatsuro Kawamoto

The stochastic block model (SBM) is a generative model revealing macroscopic structures in graphs. Bayesian methods are used for (i) cluster assignment inference and (ii) model selection for the number of clusters. In th…

Bayesian InferenceModel SelectionStochastic Block Model

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

2023-05-31 · Yucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson

Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to …

Bayesian Optimization

Fully Distributed Bayesian Optimization with Stochastic Policies

2019-02-26 · Javier Garcia-Barcos, Ruben Martinez-Cantin

Bayesian optimization has become a popular method for high-throughput computing, like the design of computer experiments or hyperparameter tuning of expensive models, where sample efficiency is mandatory. In these applic…

Bayesian OptimizationThompson Sampling

Conditionally Gaussian PAC-Bayes

2021-10-22 · Eugenio Clerico, George Deligiannidis, Arnaud Doucet

Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures nee…

Bayesian Semisupervised Learning with Deep Generative Models

2017-06-29 · Jonathan Gordon, José Miguel Hernández-Lobato

Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model…

Active LearningMissing Labels