Justin Domke
Assistant Professor
College of Computing and Information Sciences
University of Massachusetts, Amherst
email: (my last name)@cs.umass.edu
phone: +1 585 545 3241
office: CICS 208

Research Interests
Machine Learning, Probabilistic Models, Optimization, Inference

Working Papers

On the Difficulty of Unbiased Alpha Divergence Minimization, arXiv 2020 (with T. Geffner)

All Publications

Selected Recent Publications

Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization, NeurIPS 2020 (with A. Agrawal and D. Sheldon) [code]

Approximation Based Variance Reduction for Reparameterization Gradients, NeurIPS 2020 (with T. Geffner)

Provable Smoothness Guarantees for Black-Box Variational Inference, ICML 2020 [talk]

A Rule for Gradient Estimator Selection, with an Application to Variational Inference, AISTATS 2020 (with T. Geffner) [talk]

Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation, NeurIPS 2019 (with D. Sheldon) [slides] [poster] [talk]

Provable Gradient Variance Guarantees for Black-Box Variational Inference, NeurIPS 2019 [poster]

Thompson Sampling and Approximate Inference, NeurIPS 2019 (with M. Phan and Y. Abbasi-Yadkori)

Using Large Ensembles of Control Variates for Variational Inference, NeurIPS 2018 (with T. Geffner)

Importance Weighting and Variational Inference, NeurIPS 2018 (with D. Sheldon) [poster]

Weblog
justindomke.wordpress.com

Software
Graphical Models Toolbox (Matlab toolbox)
MARBL (Command line C++ tool, also usable on clusters.)

Prospective Student information

Teaching
(at UMass)
Spring 2021 Machine Learning, COMPSCI 589
Spring 2021 Graphical Models, COMPSCI 688
Spring 2020 Machine Learning, COMPSCI 589
Spring 2020 Graphical Models, COMPSCI 688
Spring 2019 Machine Learning, COMPSCI 589
Spring 2019 Graphical Models, COMPSCI 688
Fall 2017 Machine Learning, COMPSCI 589
Spring 2017 Graphical Models, COMPSCI 688
Fall 2016 Machine Learning, COMPSCI 589
(at ANU)
Semester 2 2014 Advanced Topics in Statistical Machine Learning (Structured Probabilistic Models)
Semester 2 2013 Advanced Topics in Statistical Machine Learning (Convex Optimization)
(at RIT)
Spring 2011-2012 Statistical Machine Learning
Winter 2011-2012 Discovery
Spring 2010-2011 Statistical Machine Learning
Winter 2010-2011 Discovery
Winter 2010-2011 Artificial Intelligence
Spring 2009-2010 Statistical Machine Learning