EconBase
← All papers

Quasi Black-Box Variational Inference with Natural Gradients for Bayesian Learning

Martin Magris, Mostafa Shabani, Alexandros Iosifidis

arXiv 23 May 2022 · Statistics — Machine Learning · 2 citations (OpenAlex)

arXiv:2205.11568 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We develop an optimization algorithm suitable for Bayesian learning in complex models. Our approach relies on natural gradient updates within a general black-box framework for efficient training with limited model-specific derivations. It applies within the class of exponential-family variational posterior distributions, for which we extensively discuss the Gaussian case for which the updates have a rather simple form. Our Quasi Black-box Variational Inference (QBVI) framework is readily applicable to a wide class of Bayesian inference problems and is of simple implementation as the updates of the variational posterior do not involve gradients with respect to the model parameters, nor the prescription of the Fisher information matrix. We develop QBVI under different hypotheses for the posterior covariance matrix, discuss details about its robust and feasible implementation, and provide a number of real-world applications to demonstrate its effectiveness.

Citation extraction

56
references
155
in-text mentions
56
distinct cited
0
self-citations
7,581
main-text words

appendix boundary found by appendix_command · 39% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1M. E. Khan and D. Nielsen (2018) Fast yet simple natural-gradient descent for variational inference in complex models0.9568488%
2D. P. Kingma and M. Welling (2014) Auto-encoding variational bayes0.9285380%
3M. Khan, D. Nielsen, V. Tangkaratt, W. Lin, Y. Gal, and A. Srivastava (2018) Fast and scalable bayesian deep learning by weight-perturbation in adam0.87412567%
4M. Khan and W. Lin (2017) Conjugate-computation variational inference: Converting variational inference in non-conjugate models to inferences in conjugate…0.8746467%
5J. Paisley, D. M. Blei, and M. I. Jordan (2012) Variational bayesian inference with stochastic search0.81142100%
6T. Salimans and D. A. Knowles (2014) On using control variates with stochastic approximation for variational bayes and its connection to stochastic linear regression0.81142100%
7R. Ranganath, S. Gerrish, and D. M. Blei (2014) Black box variational inference0.79410550%
8M.-N. Tran, T.-N. Nguyen, and V.-H. Dao (2021) A practical tutorial on variational bayes0.7948650%
9K. Osawa, S. Swaroop, M. E. Khan, A. Jain, R. Eschenhagen, R. E. Tur… (2019) Practical deep learning with bayesian principles0.7946450%
10M.-N. Tran, D. H. Nguyen, and D. Nguyen (2021) Variational bayes on manifolds0.77313746%

Showing the top 10 of 56 scored citations.