Entropic optimal transport yields a clustering loss with the same global optimum as log-likelihood but a better-behaved optimization surface, outperforming standard EM in experiments.
Variational Inference using Implicit Distributions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for variational inference (VI) as they are for generative modelling. Several papers have proposed GAN-like algorithms for inference, however, connections to the theory of VI are not always well understood. This paper provides a unifying review of existing algorithms establishing connections between variational autoencoders, adversarially learned inference, operator VI, GAN-based image reconstruction, and more. Secondly, the paper provides a framework for building new algorithms: depending on the way the variational bound is expressed we introduce prior-contrastive and joint-contrastive methods, and show practical inference algorithms based on either density ratio estimation or denoising.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Large empirical study of 56 optimizers on 1092 BBVI tasks finds no single winner but a selection of five suffices for near-best performance.
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
citing papers explorer
-
Large-scale empirical tuning and comparison of default optimizers for variational inference
Large empirical study of 56 optimizers on 1092 BBVI tasks finds no single winner but a selection of five suffices for near-best performance.
-
A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.