Bayesian posterior approximation with stochastic ensembles
This addresses the problem of efficient Bayesian inference for machine learning practitioners, offering an incremental improvement over existing methods.
The paper tackled approximating Bayesian posteriors using ensembles of stochastic neural networks, achieving more accurate posterior estimates than other baselines on toy and CIFAR classification tasks.
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For both tasks, we test the quality of the posteriors directly against Hamiltonian Monte Carlo simulations. Our results show that stochastic ensembles provide more accurate posterior estimates than other popular baselines for Bayesian inference.