144 citations · 324 across the 35 of their papers we have counts for
31 papers · 1 filter
Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI
Abhinav Agrawal, Justin Domke
Normalizing flow-based variational inference (flow VI) is a promising approximate inference approach, but its performance remains inconsistent across studies. Numerous algorithmic…
Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models
Jinlin Lai, Justin Domke, Daniel Sheldon
Bayesian reasoning in linear mixed-effects models (LMMs) is challenging and often requires advanced sampling techniques like Markov chain Monte Carlo (MCMC). A common approach is t…
Understanding and mitigating difficulties in posterior predictive evaluation
Abhinav Agrawal, Justin Domke
Predictive posterior densities (PPDs) are of interest in approximate Bayesian inference. Typically, these are estimated by simple Monte Carlo (MC) averages using samples from the a…
Provable convergence guarantees for black-box variational inference
Justin Domke, Guillaume Garrigos, Robert Gower
Black-box variational inference is widely used in situations where there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in exist…
Sample Average Approximation for Black-Box VI
Javier Burroni, Justin Domke, Daniel Sheldon
We present a novel approach for black-box VI that bypasses the difficulties of stochastic gradient ascent, including the task of selecting step-sizes. Our approach involves using a…
Joint control variate for faster black-box variational inference
Xi Wang, Tomas Geffner, Justin Domke
Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data sub…
Langevin Diffusion Variational Inference
Tomas Geffner, Justin Domke
Many methods that build powerful variational distributions based on unadjusted Langevin transitions exist. Most of these were developed using a wide range of different approaches a…
Variational Inference with Locally Enhanced Bounds for Hierarchical Models
Tomas Geffner, Justin Domke
Hierarchical models represent a challenging setting for inference algorithms. MCMC methods struggle to scale to large models with many local variables and observations, and variati…
Amortized Variational Inference for Simple Hierarchical Models
Abhinav Agrawal, Justin Domke
It is difficult to use subsampling with variational inference in hierarchical models since the number of local latent variables scales with the dataset. Thus, inference in hierarch…
MCMC Variational Inference via Uncorrected Hamiltonian Annealing
Tomas Geffner, Justin Domke
Given an unnormalized target distribution we want to obtain approximate samples from it and a tight lower bound on its (log) normalization constant log Z. Annealed Importance Sampl…
Empirical Evaluation of Biased Methods for Alpha Divergence Minimization
Tomas Geffner, Justin Domke
In this paper we empirically evaluate biased methods for alpha-divergence minimization. In particular, we focus on how the bias affects the final solutions found, and how this depe…
An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulations
Justin Domke
It is important to estimate the errors of probabilistic inference algorithms. Existing diagnostics for Markov chain Monte Carlo methods assume inference is asymptotically exact, an…
Approximation Based Variance Reduction for Reparameterization Gradients
Tomas Geffner, Justin Domke
Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable…
Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
Abhinav Agrawal, Daniel Sheldon, Justin Domke
Recent research has seen several advances relevant to black-box VI, but the current state of automatic posterior inference is unclear. One such advance is the use of normalizing fl…
Moment-Matching Conditions for Exponential Families with Conditioning or Hidden Data
Justin Domke
Maximum likelihood learning with exponential families leads to moment-matching of the sufficient statistics, a classic result. This can be generalized to conditional exponential fa…
A Rule for Gradient Estimator Selection, with an Application to Variational Inference
Tomas Geffner, Justin Domke
Stochastic gradient descent (SGD) is the workhorse of modern machine learning. Sometimes, there are many different potential gradient estimators that can be used. When so, choosing…
Thompson Sampling with Approximate Inference
My Phan, Yasin Abbasi-Yadkori, Justin Domke
We study the effects of approximate inference on the performance of Thompson sampling in the -armed bandit problems. Thompson sampling is a successful algorithm for online decis…
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
Justin Domke, Daniel Sheldon
Recent work in variational inference (VI) uses ideas from Monte Carlo estimation to tighten the lower bounds on the log-likelihood that are used as objectives. However, there is no…
Provable Gradient Variance Guarantees for Black-Box Variational Inference
Justin Domke
Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understa…
Provable Smoothness Guarantees for Black-Box Variational Inference
Justin Domke
Black-box variational inference tries to approximate a complex target distribution though a gradient-based optimization of the parameters of a simpler distribution. Provable conver…
Using Large Ensembles of Control Variates for Variational Inference
Tomas Geffner, Justin Domke
Variational inference is increasingly being addressed with stochastic optimization. In this setting, the gradient's variance plays a crucial role in the optimization procedure, sin…
Importance Weighting and Variational Inference
Justin Domke, Daniel Sheldon
Recent work used importance sampling ideas for better variational bounds on likelihoods. We clarify the applicability of these ideas to pure probabilistic inference, by showing the…
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
Justin Domke
Two popular classes of methods for approximate inference are Markov chain Monte Carlo (MCMC) and variational inference. MCMC tends to be accurate if run for a long enough time, whi…
Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets
Justin Domke
Inference is typically intractable in high-treewidth undirected graphical models, making maximum likelihood learning a challenge. One way to overcome this is to restrict parameters…