Skip to Main content Skip to Navigation
New interface
Poster communications

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.
Document type :
Poster communications
Complete list of metadata
Contributor : Maurizio Filippone Connect in order to contact the contributor
Submitted on : Wednesday, November 4, 2020 - 12:53:49 PM
Last modification on : Thursday, January 21, 2021 - 2:32:02 PM

Links full text


  • HAL Id : hal-02987977, version 1
  • ARXIV : 1912.00015



Simone Rossi, Sebastien Marmin, Maurizio Filippone. Efficient Approximate Inference with Walsh-Hadamard Variational Inference. 4th Workshop on Bayesian Deep Learning (NeurIPS 2019), Dec 2019, Vancouver, Canada. ⟨hal-02987977⟩



Record views