paper-with-me

Papers

Boosting Black Box Variational Inference

2018-06-06 · NeurIPS 2018 12 · Francesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar Rätsch

Approximating a probability density in a tractable manner is a central task in Bayesian statistics. Variational Inference (VI) is a popular technique that achieves tractability by choosing a relatively simple variational family. Borrowing ideas from the classic boosting framework, recent approaches attempt to \emph{boost} VI by replacing the selection of a single density with a greedily constructed mixture of densities. In order to guarantee convergence, previous works impose stringent assumptions that require significant effort for practitioners. Specifically, they require a custom implementation of the greedy step (called the LMO) for every probabilistic model with respect to an unnatural variational family of truncated distributions. Our work fixes these issues with novel theoretical and algorithmic insights. On the theoretical side, we show that boosting VI satisfies a relaxed smoothness assumption which is sufficient for the convergence of the functional Frank-Wolfe (FW) algorithm. Furthermore, we rephrase the LMO problem and propose to maximize the Residual ELBO (RELBO) which replaces the standard ELBO optimization in VI. These theoretical enhancements allow for black box implementation of the boosting subroutine. Finally, we present a stopping criterion drawn from the duality gap in the classic FW analyses and exhaustive experiments to illustrate the usefulness of our theoretical and algorithmic contributions.

📄 PDF Abstract BibTeX arXiv:1806.02185

Code (1)

ratschlab/boosting-bbvi 공식 구현 tf

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Variational Boosting: Iteratively Refining Posterior Approximations

2016-11-20 · ICML 2017 8 · Andrew C. Miller, Nicholas Foti, Ryan P. Adams

We propose a black-box variational inference method to approximate intractable distributions with an increasingly rich approximating class. Our method, termed variational boosting, iteratively refines an existing variati…

Variational Inference

Boosting Variational Inference With Locally Adaptive Step-Sizes

2021-05-19 · Gideon Dresdner, Saurav Shekhar, Fabian Pedregosa, Francesco Locatello 외

Variational Inference makes a trade-off between the capacity of the variational family and the tractability of finding an approximate posterior distribution. Instead, Boosting Variational Inference allows practitioners t…

Variational Inference

Overdispersed Black-Box Variational Inference

2016-03-03 · Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei

We introduce overdispersed black-box variational inference, a method to reduce the variance of the Monte Carlo estimator of the gradient in black-box variational inference. Instead of taking samples from the variational …

Variational Inference

Boosting Variational Inference: an Optimization Perspective

2017-08-05 · Francesco Locatello, Rajiv Khanna, Joydeep Ghosh, Gunnar Rätsch

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate…

Variational Inference

Black Box Variational Inference

2013-12-31 · Rajesh Ranganath, Sean Gerrish, David M. Blei

Variational inference has become a widely used method to approximate posteriors in complex latent variables models. However, deriving a variational inference algorithm generally requires significant model-specific analys…

Stochastic OptimizationVariational Inference