One Simple Trick to Fix Your Bayesian Neural Network

Autor:	Tempczyk, Piotr, Smoczyński, Ksawery, Smolenski-Jensen, Philip, Cygan, Marek
Rok vydání:	2022
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than its ReLU-based counterpart.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2207.13167 Zobrazit plný text záznamu View this record from Arxiv