One Simple Trick to Fix Your Bayesian Neural Network

Speaker(s)

Piotr Tempczyk

Affiliation

Uniwersytet Warszawski

Date

Nov. 3, 2022, 12:15 p.m.

Room

room 5050

Seminar

Seminarium "Machine Learning"

---

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.

---