Variational Inference

484 papers with code • 0 benchmarks • 4 datasets

Fitting approximate posteriors with variational inference transforms the inference problem into an optimization problem, where the goal is (typically) to optimize the evidence lower bound (ELBO) on the log likelihood of the data.

Greatest papers with code

Neural Variational Inference and Learning in Belief Networks

tensorflow/models 31 Jan 2014

Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well.

Latent Variable Models Variational Inference

Energy-Inspired Models: Learning with Sampler-Induced Distributions

google-research/google-research NeurIPS 2019

Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model.

Variational Inference

NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport

google-research/google-research 9 Mar 2019

Hamiltonian Monte Carlo is a powerful algorithm for sampling from difficult-to-normalize posterior distributions.

Variational Inference

What Are Bayesian Neural Network Posteriors Really Like?

google-research/google-research 29 Apr 2021

The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex.

Data Augmentation Variational Inference

Automatic structured variational inference

google-research/google-research 3 Feb 2020

However, the performance of the variational approach depends on the choice of an appropriate variational family.

Probabilistic Programming Variational Inference

Adversarial Autoencoders

eriklindernoren/PyTorch-GAN 18 Nov 2015

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution.

Data Visualization Dimensionality Reduction +4

Multi-Object Representation Learning with Iterative Variational Inference

deepmind/deepmind-research 1 Mar 2019

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.

Representation Learning Systematic Generalization +2

Pyro: Deep Universal Probabilistic Programming

uber/pyro 18 Oct 2018

Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research.

Probabilistic Programming Variational Inference

Doubly Stochastic Variational Inference for Deep Gaussian Processes

pyro-ppl/pyro NeurIPS 2017

Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice.

Gaussian Processes General Classification +1

Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm

pyro-ppl/pyro NeurIPS 2016

We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization.

Bayesian Inference Variational Inference