Efficient Approximate Inference with Walsh-Hadamard Variational Inference

Abstract

Variational inference offers scalable and flexible tools to tackle intractable Bayesian inference of modern statistical models like Bayesian neural networks and Gaussian processes. For largely over-parameterized models, however, the over-regularization property of the variational objective makes the application of variational inference challenging. Inspired by the literature on kernel methods, and in particular on structured approximations of distributions of random matrices, this paper proposes Walsh-Hadamard Variational Inference, which uses Walsh-Hadamard-based factorization strategies to reduce model parameterization, accelerate computations, and increase the expressiveness of the approximate posterior beyond fully factorized ones.

Paper accepted at the 4th Workshop on Bayesian Deep Learning (NeurIPS 2019), Vancouver, Canada. arXiv admin note: substantial text overlap with arXiv:1905.11248

References in corpus (11)

• Auto-Encoding Variational Bayes
• Variational Inference with Normalizing Flows
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Variational Dropout and the Local Reparameterization Trick
• Bayesian Compression for Deep Learning
• Variational Dropout Sparsifies Deep Neural Networks
• Orthogonal Random Features
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Random Feature Expansions for Deep Gaussian Processes
• Good Initializations of Variational Bayes for Deep Models
• Walsh-Hadamard Variational Inference for Bayesian Deep Learning