D. J. Sutherland
I'm a Research Assistant Professor at TTIC; in January 2021, I'll start as an Assistant Professor in UBC Computer Science.
If you're already at UBC and interested in working with me starting next year, get in touch! Prospective students, though, should simply apply to the department and indicate your interest in working with me in the application.
djs [at] djsutherland [dot] ml, CV, ORCID, GPG key / keybase.
My research interests include:
- Learning and testing on sets and distributions: two-sample tests, evaluating and training generative models, density estimation, distribution regression.
- Evaluating and training implicit generative models, particularly GANs.
- Approximate kernel embeddings, e.g. random Fourier features and the Nyström approximation.
- Kernels defined by deep networks.
- Active learning, especially in nonstandard settings like searching for large-scale patterns.
I was previously a postdoc with Arthur Gretton at the Gatsby Computational Neuroscience Unit, University College London, and I did my Ph.D. at Carnegie Mellon University with Jeff Schneider. See also various code on github, or my crossvalidated/stackoverflow profiles.
Publications and selected talks are listed below.
Publications
Below, ** denotes equal contribution. Also available as a .bib file, and most of these are on Google Scholar.
Journal and Low-Acceptance-Rate Conference Papers
On Uniform Convergence and Low-Norm Interpolation Learning.
Neural Information Processing Systems
(NeurIPS)
2020.
[arXiv]
[Penn State talk]
Learning Deep Kernels for Non-Parametric Two-Sample Tests.
International Conference on Machine Learning
(ICML)
2020.
Learning deep kernels for exponential family densities.
International Conference on Machine Learning
(ICML)
2019.
On gradient regularizers for MMD GANs.
Neural Information Processing Systems
(NeurIPS)
2018.
Demystifying MMD GANs.
International Conference on Learning Representations
(ICLR)
2018.
Efficient and principled score estimation with Nyström kernel exponential families.
Artificial Intelligence and Statistics
(AISTATS)
2018.
Selected for oral presentation.
Bayesian Approaches to Distribution Regression.
Artificial Intelligence and Statistics
(AISTATS)
2018.
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
International Conference on Learning Representations
(ICLR)
2017.
Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning.
The Astrophysical Journal
(ApJ)
831, 2, 135.
2016.
Linear-time Learning on Distributions with Approximate Kernel Embeddings.
AAAI Conference on Artificial Intelligence
(AAAI)
2016.
On the Error of Random Fourier Features.
Uncertainty in Artificial Intelligence
(UAI)
2015.
Chapter 3 / Section 4.1 of my thesis supersedes this paper, fixing a few errors in constants and providing more results.
Active Pointillistic Pattern Search.
Artificial Intelligence and Statistics
(AISTATS)
2015.
A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters.
The Astrophysical Journal
(ApJ)
803, 2, 50.
2015.
Active learning and search on low-rank matrices.
Knowledge Discovery and Data Mining
(KDD)
2013.
Selected for oral presentation.
Nonparametric kernel estimators for image classification.
Computer Vision and Pattern Recognition
(CVPR)
2012.
Dissertations
Scalable, Flexible, and Active Learning on Distributions.
Computer Science Department, Carnegie Mellon University. Ph.D. thesis,
2016.
Integrating Human Knowledge into a Relational Learning System.
Computer Science Department, Swarthmore College. B.A. thesis,
2011.
[pdf]
Technical Reports, Posters, etc.
Bayesian Approaches to Distribution Regression.
Learning on Distributions, Functions, Graphs and Groups, NeurIPS
2017.
Selected for oral presentation.
Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata.
Technical report
2016.
List Mode Regression for Low Count Detection.
IEEE Nuclear Science Symposium
(IEEE NSS/MIC)
2016.
Linear-time Learning on Distributions with Approximate Kernel Embeddings.
Feature Extraction: Modern Questions and Challenges, NeurIPS
2015.
Finding Representative Objects with Sparse Modeling.
CMU 10-725 Optimization course project
2012.
Best poster award.
[pdf]
Grounding Conceptual Knowledge with Spatio-Temporal Multi-Dimensional Relational Framework Trees.
Technical report
2012.
[pdf]
Invited talks
Slides for conference and workshop talks directly for a paper are linked next to the paper above.
Can Uniform Convergence Explain Interpolation Learning?.
October 2020.
Penn State, Statistics colloquium.
Related papers:
On Uniform Convergence and Low-Norm Interpolation Learning.
[slides]
[slides (pdf)]
Tutorial: Interpretable Comparison of Distributions and Models.
December 2019.
Neural Information Processing Systems
(NeurIPS).
Related papers:
Learning Deep Kernels for Non-Parametric Two-Sample Tests, Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
With Arthur Gretton and Wittawat Jitkrittum.
Better GANs by Using Kernels.
October 2019.
University of Massachusetts Amherst, College of Information and Computer Sciences.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
[slides]
Introduction to Generative Adversarial Networks.
June 2019.
Machine Learning Crash Course
(MLCC).
[slides]
Kernel Distances for Better Deep Generative Models.
September 2018.
Advances in Kernel Methods, GPSS.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
[slides]
Better GANs by using the MMD.
June 2018.
Facebook AI Research New York.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
[slides]
Efficiently Estimating Densities and Scores with Kernel Exponential Families.
June 2018.
Gatsby Tri-Center Meeting.
Related papers:
Efficient and principled score estimation with Nyström kernel exponential families.
[slides]
Better GANs by using the MMD.
June 2018.
Machine Learning reading group, Google New York.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
[slides]
Better GANs by using the MMD.
June 2018.
Machine Learning reading group, Columbia University.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
No slides actually used at the talk because of a projector mishap,
but they would have been the same as
the Google talk.
Advances in GANs based on the MMD.
May 2018.
Machine Learning Seminar, University of Sheffield.
Related papers:
Demystifying MMD GANs, On gradient regularizers for MMD GANs.
Efficient and principled score estimation with kernel exponential families.
December 2017.
Approximating high dimensional functions, Alan Turing Institute.
Related papers:
Efficient and principled score estimation with Nyström kernel exponential families.
Efficient and principled score estimation with kernel exponential families.
December 2017.
Computational Statistics and Machine Learning seminar, University College London.
Related papers:
Efficient and principled score estimation with Nyström kernel exponential families.
[slides]
Evaluating and Training Implicit Generative Models with Two-Sample Tests.
August 2017.
Implicit Models, ICML.
Related papers:
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
[slides]
Two-Sample Tests, Integral Probability Metrics, and GAN Objectives.
April 2017.
Theory of Generative Adversarial Networks, DALI.
Related papers:
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
February 2017.
Computational Statistics and Machine Learning seminar, Oxford University.
Related papers:
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
[slides]