Geoffrey Gordon

Core Industry Member
Geoffrey Gordon
Adjunct Professor, McGill University, Microsoft Research
Geoffrey Gordon

Dr. Gordon is the Research Director for the Microsoft Research Montréal lab, and a Professor in the Machine Learning Department at Carnegie Mellon University. He has also served as Interim Department Head and as Associate Department Head for Education for the Machine Learning Department. Dr. Gordon’s research has focused on artificially-intelligent systems that are capable of long-term thinking such as reasoning ahead to solve a problem, planning a sequence of actions or inferring unseen properties from observations. Particularly, he looks at how to combine machine learning with these long-term thinking tasks. Dr. Gordon received his B.A. in Computer Science from Cornell University in 1991, and his PhD in Computer Science from Carnegie Mellon University in 1999. His research interests include artificial intelligence, statistical machine learning, educational data, game theory, multi-robot systems, and planning in probabilistic, adversarial, and general-sum domains. His previous appointments include Visiting Professor at the Stanford Computer Science Department and Principal Scientist at Burning Glass Technologies in San Diego.

Publications

2020-12

Fundamental Limits and Tradeoffs in Invariant Representation Learning
Han Zhao, Chen Dan, Bryon Aragam, Tommi S. Jaakkola, Geoffrey J. Gordon and Pradeep Ravikumar
arXiv preprint arXiv:2012.10713
(2020-12-19)
arxiv.orgPDF

2020-11

An Empirical Investigation of Beam-Aware Training in Supertagging.
Renato Negrinho, Matthew R. Gormley and Geoffrey J. Gordon
EMNLP 2020
(2020-11-01)
dblp.uni-trier.dePDF

2020-10

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation.
Han Zhao, Jianfeng Chi, Yuan Tian and Geoffrey J. Gordon
arXiv: Learning
(2020-10-26)
arxiv.orgPDF
An Empirical Investigation of Beam-Aware Training in Supertagging
Renato Negrinho, Matthew R. Gormley and Geoffrey J. Gordon
arXiv preprint arXiv:2010.04980
(2020-10-10)
arxiv.orgPDF

2020-09

Graph Adversarial Networks: Protecting Information against Adversarial Attacks.
Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka and Ruslan Salakhutdinov
arXiv preprint arXiv:2009.13504
(2020-09-28)
arxiv.orgPDF

2020-05

De-Aliasing States In Dialogue Modelling With Inverse Reinforcement Learning
Layla El Asri, Adam Trischler and Geoff Gordon
(venue unknown)
(2020-05-15)
www.microsoft.com

2020-04

Conditional Learning of Fair Representations
Han Zhao, Amanda Coston, Tameem Adel and Geoffrey J. Gordon

2020-03

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang and Geoffrey J. Gordon
NEURIPS 2020
(2020-03-10)
papers.nips.cc
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift.
Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang and Geoffrey J. Gordon
arXiv preprint arXiv:2003.04475
(2020-03-10)
www.microsoft.comPDF

2020-02

Learning General Latent-Variable Graphical Models with Predictive Belief Propagation
Borui Wang and Geoffrey Gordon
AAAI 2020
(2020-02-07)
aaai.orgPDF

2020-01

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
Han Zhao, Jianfeng Chi, Yuan Tian and Geoffrey J. Gordon
NEURIPS 2020
(2020-01-01)
papers.nips.cc

2019-12

Inherent Tradeoffs in Learning Fair Representation
Han Zhao and Geoff Gordon
NEURIPS 2019
(2019-12-08)
papers.nips.ccPDF
Learning Neural Networks with Adaptive Regularization
Han Zhao, Yao-Hung Tsai, Ruslan Salakhutdinov and Geoffrey Gordon
Towards modular and programmable architecture search
Renato Negrinho, Matthew Gormley, Geoffrey Gordon, Darshan Patil, Nghia Le and Daniel Ferreira
NEURIPS 2019
(2019-12-08)
papers.nips.ccPDF
Expressiveness and Learning of Hidden Quantum Markov Models.
Sandesh Adhikary, Siddarth Srinivasan, Geoffrey J. Gordon and Byron Boots

2019-11

A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng, Remi Tachet des Combes, Byron Boots and Geoffrey J. Gordon

2019-09

Towards modular and programmable architecture search
Renato Negrinho, Darshan Patil, Nghia Le, Daniel Ferreira, Matthew Gormley and Geoffrey Gordon
arXiv preprint arXiv:1909.13404
(2019-09-30)
arxiv.orgPDF
Adversarial Privacy Preservation under Attribute Inference Attack
Han Zhao, Jianfeng Chi, Yuan Tian and Geoffrey J. Gordon
arXiv preprint arXiv:1906.07902
(2019-09-25)
ui.adsabs.harvard.eduPDF

2019-06

Adversarial Task-Specific Privacy Preservation under Attribute Attack.
Han Zhao, Jianfeng Chi, Yuan Tian and Geoffrey J. Gordon
arXiv: Learning
(2019-06-19)
dblp.uni-trier.dePDF
Inherent Tradeoffs in Learning Fair Representations
Han Zhao and Geoffrey J. Gordon
arXiv preprint arXiv:1906.08386
(2019-06-19)
arxiv.orgPDF
On Learning Invariant Representation for Domain Adaptation
Han Zhao, Remi Tachet des Combes, Kun Zhang and Geoff Gordon

2019-05

Deep Generative and Discriminative Domain Adaptation
Han Zhao, Junjie Hu, Zhenyao Zhu, Adam Coates and Geoff Gordon
AAMAS 2019
(2019-05-08)
dl.acm.org
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Mariya Toneva, Alessandro Sordoni, Remi Combes, Adam Trischler, Yoshua Bengio and Geoffrey Gordon

2018-12

Dual Policy Iteration
Wen Sun, Geoffrey Gordon, Byron Boots and J. Bagnell
NEURIPS 2018
(2018-12-03)
papers.nips.ccPDF
Learning Beam Search Policies via Imitation Learning
Renato Negrinho, Matthew Gormley and Geoffrey Gordon
Adversarial Multiple Source Domain Adaptation
Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, Joao P Costeira and Geoffrey Gordon
NEURIPS 2018
(2018-12-03)
papers.nips.ccPDF

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }