One Simple Trick to Fix Your Bayesian Neural Network

Prelegent(ci)

Piotr Tempczyk

Afiliacja

Uniwersytet Warszawski

Termin

3 listopada 2022 12:15

Pokój

p. 5050

Seminarium

Seminarium "Uczenie maszynowe"

---

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.

---