paper-with-me

Papers

Alpha-Divergences in Variational Dropout

2017-11-12 · Bogdan Mazoure, Riashat Islam

We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a general framework for estimating the evidence lower bound (ELBO) in Variational Bayes. In this work, we extend the SGVB estimator with using Alpha-Divergences, which are alternative to divergences to VI' KL objective. The Gaussian dropout can be seen as a local reparametrization trick of the SGVB objective. We extend the Variational Dropout to use alpha divergences for variational inference. Our results compare $\alpha$-divergence variational dropout with standard variational dropout with correlated and uncorrelated weight noise. We show that the $\alpha$-divergence with $\alpha \rightarrow 1$ (or KL divergence) is still a good measure for use in variational inference, in spite of the efficient use of Alpha-divergences for Dropout VI \cite{Li17}. $\alpha \rightarrow 1$ can yield the lowest training error, and optimizes a good lower bound for the evidence lower bound (ELBO) among all values of the parameter $\alpha \in [0,\infty)$.

📄 PDF Abstract BibTeX arXiv:1711.04345

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Dropout Inference in Bayesian Neural Networks with Alpha-divergences

2017-03-08 · ICML 2017 8 · Yingzhen Li, Yarin Gal

To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical ap…

Variational Inference

Variational Inference with Tail-adaptive f-Divergence

2018-10-29 · NeurIPS 2018 12 · Dilin Wang, Hao liu, Qiang Liu

Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using {\alpha}-divergences (with positive …

Deep Reinforcement LearningReinforcement LearningVariational Inference

Function-space regularized Rényi divergences

2022-10-10 · Jeremiah Birrell, Yannis Pantazis, Paul Dupuis, Markos A. Katsoulakis 외

We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space. These new objects are defined by taking the infimal convolution of the stan…

Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation

2020-02-25 · Yuki Ohnishi, Jean Honorio

We introduce several novel change of measure inequalities for two families of divergences: $f$-divergences and $\alpha$-divergences. We show how the variational representation for $f$-divergences leads to novel change of…

Perturbative Black Box Variational Inference

2017-09-21 · NeurIPS 2017 12 · Robert Bamler, Cheng Zhang, Manfred Opper, Stephan Mandt

Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences. In this paper, we view…

Gaussian ProcessesVariational Inference