Dangers of Bayesian Model Averaging under Covariate Shift

Autor:	Izmailov, Pavel, Nicholson, Patrick, Lotfi, Sanae, Wilson, Andrew Gordon
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data. However, Bayesian neural networks (BNNs) with high-fidelity approximate inference via full-batch Hamiltonian Monte Carlo achieve poor generalization under covariate shift, even underperforming classical estimation. We explain this surprising result, showing how a Bayesian model average can in fact be problematic under covariate shift, particularly in cases where linear dependencies in the input features cause a lack of posterior contraction. We additionally show why the same issue does not affect many approximate inference procedures, or classical maximum a-posteriori (MAP) training. Finally, we propose novel priors that improve the robustness of BNNs to many sources of covariate shift. Comment: NeurIPS 2021. Code is available at https://github.com/izmailovpavel/bnn_covariate_shift
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.11905 Zobrazit plný text záznamu View this record from Arxiv