clm_c00124ceFirst, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods.
arXiv 1312.6114 · stat.ML cs.LG
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_c00124ceFirst, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods.
clm_b4b96ad6Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition … (excerpt)
clm_c6ee1c8aWe show how a reparameterization of the variational lower bound yields a simple differentiable unbiased estimator of the lower bound; this SGVB (Stochastic Gradient Variational Bayes) estimator can be used … (excerpt)
clm_199a284dFor the case of an i.i.d. dataset and continuous latent variables per datapoint, we propose the Auto- Encoding VB (AEVB) algorithm.
clm_90d1bf9fWe have introduced a novel estimator of the variational lower bound, Stochastic Gradient VB (SGVB), for efficient approximate inference with continuous latent variables.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1312.6114) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.