English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although with progress in introducing auxiliary amortized inference models,learning discrete latent variable models is still challenging. In this paper,we show that the annoying difficulty of obtaining reliable stochastic gradientsfor the inference model and the drawback of indirectly optimizing the targetlog-likelihood can be gracefully addressed in a new method based on stochasticapproximation (SA) theory of the Robbins-Monro type. Specifically, we proposeto directly maximize the target log-likelihood and simultaneously minimize theinclusive divergence between the posterior and the inference model. Theresulting learning algorithm is called joint SA (JSA). To the best of ourknowledge, JSA represents the first method that couples an SA version of the EM(expectation-maximization) algorithm (SAEM) with an adaptive MCMC procedure.Experiments on several benchmark generative modeling and structured predictiontasks show that JSA consistently outperforms recent competitive algorithms,with faster convergence, better final likelihoods, and lower variance ofgradient estimates.

Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models