paper-with-me

Papers

Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form

2013-06-04 · Diederik P. Kingma

We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally deterministic given their parents and a set of independent auxiliary variables. Variables of mod- els in this auxiliary form have much larger Markov blankets, leading to significant speedups in gradient-based inference, e.g. rapid mixing Hybrid Monte Carlo and efficient gradient-based optimization. The relative efficiency is confirmed in ex- periments.

📄 PDF Abstract BibTeX arXiv:1306.0733

Code (0)

등록된 구현이 없습니다.

Tasks

Form

Similar Papers 제목 키워드 기반

Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation

2020-09-15 · EMNLP 2020 11 · Jason Lee, Raphael Shu, Kyunghyun Cho

We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation…

de-enMachine TranslationSentenceTranslation

Discretely Relaxing Continuous Variables for tractable Variational Inference

2018-12-01 · NeurIPS 2018 12 · Trefor Evans, Prasanth Nair

We explore a new research direction in Bayesian variational inference with discrete latent variable priors where we exploit Kronecker matrix algebra for efficient and exact computations of the evidence lower bound (ELBO)…

Variational Inference

Discretely Relaxing Continuous Variables for tractable Variational Inference

2018-09-12 · NeurIPS 2018 · Trefor W. Evans, Prasanth B. Nair

We explore a new research direction in Bayesian variational inference with discrete latent variable priors where we exploit Kronecker matrix algebra for efficient and exact computations of the evidence lower bound (ELBO)…

Variational Inference

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

2017-03-21 · NeurIPS 2017 12 · George Tucker, andriy mnih, Chris J. Maddison, Dieterich Lawson 외

Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent w…

Natural Gradient Hybrid Variational Inference with Application to Deep Mixed Models

2023-02-27 · Weiben Zhang, Michael Stanley Smith, Worapree Maneesoonthorn, Ruben Loaiza-Maya

Stochastic models with global parameters and latent variables are common, and for which variational inference (VI) is popular. However, existing methods are often either slow or inaccurate in high dimensions. We suggest …

Stochastic OptimizationVariational Inference