Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation

Abstract

We introduce a novel combination of Bayesian Models (BMs) and Neural Networks (NNs) for making predictions with a minimum expected risk. Our approach combines the best of both worlds, the data efficiency and interpretability of a BM with the speed of a NN. For a BM, making predictions with the lowest expected loss requires integrating over the posterior distribution. When exact inference of the posterior predictive distribution is intractable, approximation methods are typically applied, e.g. Monte Carlo (MC) simulation. For MC, the variance of the estimator decreases with the number of samples - but at the expense of increased computational cost. Our approach removes the need for iterative MC simulation on the CPU at prediction time. In brief, it works by fitting a NN to synthetic data generated using the BM. In a single feed-forward pass, the NN gives a set of point-wise approximations to the BM's posterior predictive distribution for a given observation. We achieve risk minimized predictions significantly faster than standard methods with a negligible loss on the test dataset. We combine this approach with Active Learning to minimize the amount of data required for fitting the NN. This is done by iteratively labeling more data in regions with high predictive uncertainty of the NN.

arXiv comment8 pages, 3 figures. Accepted for publishing at IJCNN2021

References in corpus (11)

• Auto-Encoding Variational Bayes
• Variational Inference: A Review for Statisticians
• Language Models are Few-Shot Learners
• Variational Inference with Normalizing Flows
• Neural Network with Unbounded Activation Functions is Universal Approximator
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• A Bayesian Data Augmentation Approach for Learning Deep Models
• The Case for Bayesian Deep Learning
• Dropout-based Active Learning for Regression
• Uncertainty in Neural Networks: Approximately Bayesian Ensembling