atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Rényi Divergence Variational Inference

NeurIPS 2016 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Variational inference theory and gradients · 70 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use VR-max instead of IWAEVAE training on Frey Face with K = 50 and batch size M = 100 on CPU · Frey Faceseconds per epoch: 29.0s -> 9.7sHelped
Use alpha = 0.5 instead of alpha = 0 or alpha = -infinityVAE maximum-likelihood training · Frey Facetest log-likelihood: 1374.64±5.62Hurt
Use alpha = 0.5 instead of alpha = 0 or alpha = -infinityVAE maximum-likelihood training · MNISTtest log-likelihood: -85.50Hurt
Use small negative alpha values such as -1.0 or -2.0VAE training · Frey Facetest log-likelihoodHelped
Use VR-max instead of IWAEVAE training · Frey Face, Caltech 101 Silhouettes, MNIST, and OMNIGLOTtest log-likelihoodNo clear effect
Increase the number of Monte Carlo samples KVR-alpha bound estimation · Frey Face test datapointsgap to the estimated log-likelihoodHelped
Decrease alpha toward negative infinityVR-alpha bound estimation · Frey Face test datapointsgap to the estimated log-likelihoodHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy