Geoffrey J. Gordon

is this you? claim profile

∙ 0 followers
Microsoft ∙ Carnegie Mellon University

Professor, Machine Learning Department at Carnegie Mellon University, Research Director, Microsoft Montréal

Successor Feature Sets: Generalizing Successor Representations Across Policies

Successor-style representations have many advantages for reinforcement l...
03/03/2021 ∙ by Kianté Brantley, et al. ∙ 8 ∙ share

read it
Understanding and Mitigating Accuracy Disparity in Regression

With the widespread deployment of large-scale prediction systems in high...
02/24/2021 ∙ by Jianfeng Chi, et al. ∙ 0 ∙ share

read it
Fundamental Limits and Tradeoffs in Invariant Representation Learning

Many machine learning applications involve learning representations that...
12/19/2020 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
An Empirical Investigation of Beam-Aware Training in Supertagging

Structured prediction is often approached by training a locally normaliz...
10/10/2020 ∙ by Renato Negrinho, et al. ∙ 0 ∙ share

read it
Conditional Learning of Fair Representations

We propose a novel algorithm for learning fair representations that can ...
10/16/2019 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
Learning Neural Networks with Adaptive Regularization

Feed-forward neural networks can be understood as a combination of an in...
07/14/2019 ∙ by Han Zhao, et al. ∙ 3 ∙ share

read it
Inherent Tradeoffs in Learning Fair Representation

With the prevalence of machine learning in high-stakes applications, esp...
06/19/2019 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
Adversarial Task-Specific Privacy Preservation under Attribute Attack

With the prevalence of machine learning services, crowdsourced data cont...
06/19/2019 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
On Learning Invariant Representation for Domain Adaptation

Due to the ability of deep neural nets to learn rich representations, re...
01/27/2019 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
An Empirical Study of Example Forgetting during Deep Neural Network Learning

Inspired by the phenomenon of catastrophic forgetting, we investigate th...
12/12/2018 ∙ by Mariya Toneva, et al. ∙ 14 ∙ share

read it
Learning Beam Search Policies via Imitation Learning

Beam search is widely used for approximate decoding in structured predic...
11/01/2018 ∙ by Renato Negrinho, et al. ∙ 0 ∙ share

read it
Dual Policy Iteration

Recently, a novel class of Approximate Policy Iteration (API) algorithms...
05/28/2018 ∙ by Wen Sun, et al. ∙ 0 ∙ share

read it
Unsupervised Learning for Nonlinear PieceWise Smooth Hybrid Systems

This paper introduces a novel system identification and tracking method ...
10/02/2017 ∙ by Gilwoo Lee, et al. ∙ 0 ∙ share

read it
Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

While domain adaptation has been actively researched in recent years, mo...
05/26/2017 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
Supervised Learning for Controlled Dynamical System Learning

We develop a framework for reducing the identification of controlled dyn...
02/12/2017 ∙ by Ahmed Hefny, et al. ∙ 0 ∙ share

read it
Constant Size Molecular Descriptors For Use With Machine Learning

A set of molecular descriptors whose length is independent of molecular ...
01/23/2017 ∙ by Christopher R. Collins, et al. ∙ 0 ∙ share

read it
Galerkin Methods for Complementarity Problems and Variational Inequalities

Complementarity problems and variational inequalities arise in a wide va...
06/20/2013 ∙ by Geoffrey J. Gordon, et al. ∙ 0 ∙ share

read it
A Spectral Learning Approach to Range-Only SLAM

We present a novel spectral learning algorithm for simultaneous localiza...
07/10/2012 ∙ by Byron Boots, et al. ∙ 0 ∙ share

read it
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Sequential prediction problems such as imitation learning, where future ...
11/02/2010 ∙ by Stéphane Ross, et al. ∙ 0 ∙ share

read it
Predictive State Temporal Difference Learning

We propose a new approach to value function approximation which combines...
10/30/2010 ∙ by Byron Boots, et al. ∙ 0 ∙ share

read it
Closing the Learning-Planning Loop with Predictive State Representations

A central problem in artificial intelligence is that of planning to maxi...
12/12/2009 ∙ by Byron Boots, et al. ∙ 0 ∙ share

read it
Reduced-Rank Hidden Markov Models

We introduce the Reduced-Rank Hidden Markov Model (RR-HMM), a generaliza...
10/06/2009 ∙ by Sajid M. Siddiqi, et al. ∙ 0 ∙ share

read it

Geoffrey J. Gordon

Featured Co-authors

Yoshua Bengio

Ruslan Salakhutdinov

Kun Zhang

Byron Boots

Pradeep Ravikumar

Yuan Tian

Adam Trischler

José M. F. Moura

Wen Sun

J Andrew Bagnell

Han Zhao

Successor Feature Sets: Generalizing Successor Representations Across Policies

Understanding and Mitigating Accuracy Disparity in Regression

Fundamental Limits and Tradeoffs in Invariant Representation Learning

An Empirical Investigation of Beam-Aware Training in Supertagging

Conditional Learning of Fair Representations

Learning Neural Networks with Adaptive Regularization

Inherent Tradeoffs in Learning Fair Representation

Adversarial Task-Specific Privacy Preservation under Attribute Attack

On Learning Invariant Representation for Domain Adaptation

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Learning Beam Search Policies via Imitation Learning

Dual Policy Iteration

Unsupervised Learning for Nonlinear PieceWise Smooth Hybrid Systems

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

Supervised Learning for Controlled Dynamical System Learning

Constant Size Molecular Descriptors For Use With Machine Learning

Galerkin Methods for Complementarity Problems and Variational Inequalities

A Spectral Learning Approach to Range-Only SLAM

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Predictive State Temporal Difference Learning

Closing the Learning-Planning Loop with Predictive State Representations

Reduced-Rank Hidden Markov Models