paper-with-me

Papers

A Deterministic Global Optimization Method for Variational Inference

2017-03-21 · Hachem Saddiki, Andrew C. Trapp, Patrick Flaherty

Variational inference methods for latent variable statistical models have gained popularity because they are relatively fast, can handle large data sets, and have deterministic convergence guarantees. However, in practice it is unclear whether the fixed point identified by the variational inference algorithm is a local or a global optimum. Here, we propose a method for constructing iterative optimization algorithms for variational inference problems that are guaranteed to converge to the $\epsilon$-global variational lower bound on the log-likelihood. We derive inference algorithms for two variational approximations to a standard Bayesian Gaussian mixture model (BGMM). We present a minimal data set for empirically testing convergence and show that a variational inference algorithm frequently converges to a local optimum while our algorithm always converges to the globally optimal variational lower bound. We characterize the loss incurred by choosing a non-optimal variational approximation distribution suggesting that selection of the approximating variational distribution deserves as much attention as the selection of the original statistical model for a given data set.

📄 PDF Abstract BibTeX arXiv:1703.07169

Code (0)

등록된 구현이 없습니다.

Tasks

global-optimizationVariational Inference

Similar Papers 제목 키워드 기반

Stochastic Annealing for Variational Inference

2015-05-25 · San Gultekin, Aonan Zhang, John Paisley

We empirically evaluate a stochastic annealing strategy for Bayesian posterior optimization with variational inference. Variational inference is a deterministic approach to approximate posterior inference in Bayesian mod…

Variational Inference

Moment-Based Variational Inference for Stochastic Differential Equations

2021-03-01 · Christian Wildner, Heinz Koeppl

Existing deterministic variational inference approaches for diffusion processes use simple proposals and target the marginal density of the posterior. We construct the variational process as a controlled version of the p…

Variational Inference

Improving Explorability in Variational Inference with Annealed Variational Objectives

2018-09-06 · NeurIPS 2018 12 · Chin-wei Huang, Shawn Tan, Alexandre Lacoste, Aaron Courville

Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process can still limit the density that is ultimately learned. We demonstrate the drawbacks …

Variational Inference

Proximity Variational Inference

2017-05-24 · Jaan Altosaar, Rajesh Ranganath, David M. Blei

Variational inference is a powerful approach for approximate posterior inference. However, it is sensitive to initialization and can be subject to poor local optima. In this paper, we develop proximity variational infere…

Variational Inference

Variational Tempering

2014-11-07 · Stephan Mandt, James McInerney, Farhan Abrol, Rajesh Ranganath 외

Variational inference (VI) combined with data subsampling enables approximate posterior inference over large data sets, but suffers from poor local optima. We first formulate a deterministic annealing approach for the ge…

Variational Inference