MaxEntropy Pursuit Variational Inference
Machine Learning
2019-05-21 v1 Machine Learning
Abstract
One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as mean-field models and accuracy of inference. We propose a variant of a greedy approximation of the posterior distribution with tractable base learners. Using Max-Entropy approach, we obtain a well-defined optimization problem. We demonstrate the ability of the method to capture complex multimodal posterior via continual learning setting for neural networks.
Cite
@article{arxiv.1905.07855,
title = {MaxEntropy Pursuit Variational Inference},
author = {Evgenii Egorov and Kirill Neklydov and Ruslan Kostoev and Evgeny Burnaev},
journal= {arXiv preprint arXiv:1905.07855},
year = {2019}
}
Comments
10 pages, 1 figure