
A Rule for Gradient Estimator Selection, with an Application to Variational Inference
Stochastic gradient descent (SGD) is the workhorse of modern machine lea...
read it

A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
Two popular classes of methods for approximate inference are Markov chai...
read it

Clamping Improves TRW and Mean Field Approximations
We examine the effect of clamping variables for approximate inference in...
read it

Maximum Likelihood Learning With Arbitrary Treewidth via FastMixing Parameter Sets
Inference is typically intractable in hightreewidth undirected graphica...
read it

Projecting Markov Random Field Parameters for Fast Mixing
Markov chain Monte Carlo (MCMC) algorithms are simple and extremely powe...
read it

Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems
Recent advances in optimization theory have shown that smooth strongly c...
read it

Structured Learning via Logistic Regression
A successful approach to structured learning is to write the learning ob...
read it

Projecting Ising Model Parameters for Fast Mixing
Inference in general Ising models is difficult, due to high treewidth ma...
read it

Learning Graphical Model Parameters with Approximate Marginal Inference
Likelihood basedlearning of graphical models faces challenges of comput...
read it

Conditional Inference in Pretrained Variational Autoencoders via Crosscoding
Variational Autoencoders (VAEs) are a popular generative model, but one ...
read it

Importance Weighting and Varational Inference
Recent work used importance sampling ideas for better variational bounds...
read it

Importance Weighting and Variational Inference
Recent work used importance sampling ideas for better variational bounds...
read it

Using Large Ensembles of Control Variates for Variational Inference
Variational inference is increasingly being addressed with stochastic op...
read it

Provable Smoothness Guarantees for BlackBox Variational Inference
Blackbox variational inference tries to approximate a complex target di...
read it

Provable Gradient Variance Guarantees for BlackBox Variational Inference
Recent variational inference methods use stochastic gradient estimators ...
read it

Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
Recent work in variational inference (VI) uses ideas from Monte Carlo es...
read it

Thompson Sampling and Approximate Inference
We study the effects of approximate inference on the performance of Thom...
read it

Advances in BlackBox VI: Normalizing Flows, Importance Weighting, and Optimization
Recent research has seen several advances relevant to blackbox VI, but ...
read it