Portrait of Geoff Gordon

Geoff Gordon

Affiliate Member
Professor, Carnegie Mellon University, Department of Machine Learning
Research Topics
Optimization
Reasoning
Reinforcement Learning
Website
Google Scholar

Biography

Geoffrey Gordon is an adjunct professor in the Machine Learning Department at Carnegie Mellon University. He previously served as interim department head and associate department head for education in Carnegie Mellon’s Machine Learning Department.

In general, Gordon’s interests lie in AI, statistical machine learning, educational data, game theory, multi-robot systems, and planning in probabilistic, adversarial, and general-sum domains.

More specifically, his 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. In particular, he looks at how to combine machine learning with these long-term thinking tasks.

Gordon received his BSc in computer science from Cornell University in 1991, and his PhD in computer science from Carnegie Mellon University in 1999. His previous appointments include visiting professor at Stanford’s Computer Science Department, and principal scientist at Burning Glass Technologies in San Diego.

Publications

Meta-Analysis with Untrusted Data
Shiva Kaul
Geoff Gordon
Meta-analyses are usually conducted on small amounts of “trusted” data, ideally from randomized, controlled trials. Excluding untrusted … (see more)(observational) data — such as medical records and related scientific literature — avoids potential confounding and ensures unbiased conclusions. Unfortunately, this exclusion can reduce predictive accuracy to the point of clinical irrelevance, especially when trials are heterogeneous. This paper shows how untrusted data can be safely incorporated into meta-analysis, improving predictions without sacrificing rigor or introducing unproven assumptions. Our approach, called conformal meta-analysis, consists of (1) learning a (potentially flawed) prior distribution from the untrusted data, (2) using the prior and trusted data to derive a simple, fully-conformal prediction interval for the observed trial effect, and (3) analytically extracting an interval for the true (unobserved) effect. In multiple experiments on healthcare datasets, our algorithms deliver tighter, sounder intervals than traditional ones. This paper conceptually realigns meta-analysis as a foundation for evidence-based medicine, embracing heterogeneity and untrusted data for more nuanced, precise predictions.
2025-02-17
Proceedings of the 4th Machine Learning for Health Symposium (published)
proceedings.mlr.press
When is Transfer Learning Possible?
My Phan
Kianté Brantley
Stephanie Milani
Soroush Mehri
Gokul Swamy
Geoff Gordon
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng
Remi Tachet des Combes
Byron Boots
Geoff Gordon
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (see more)any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Expressiveness and Learning of Hidden Quantum Markov Models
Sandesh M. Adhikary
Siddarth Srinivasan
Geoff Gordon
Byron Boots
Extending classical probabilistic reasoning using the quantum mechanical view of probability has been of recent interest, particularly in th… (see more)e development of hidden quantum Markov models (HQMMs) to model stochastic processes. However, there has been little progress in characterizing the expressiveness of such models and learning them from data. We tackle these problems by showing that HQMMs are a special subclass of the general class of observable operator models (OOMs) that do not suffer from the \emph{negative probability problem} by design. We also provide a feasible retraction-based learning algorithm for HQMMs using constrained gradient descent on the Stiefel manifold of model parameters. We demonstrate that this approach is faster and scales to larger models than previous learning algorithms.
2020-01-01
AISTATS (published)
proceedings.mlr.press
arxiv.org
Expressiveness and Learning of Hidden Quantum Markov Models
Sandesh M. Adhikary
Siddarth Srinivasan
Geoff Gordon
Byron Boots
Extending classical probabilistic reasoning using the quantum mechanical view of probability has been of recent interest, particularly in th… (see more)e development of hidden quantum Markov models (HQMMs) to model stochastic processes. However, there has been little progress in characterizing the expressiveness of such models and learning them from data. We tackle these problems by showing that HQMMs are a special subclass of the general class of observable operator models (OOMs) that do not suffer from the \emph{negative probability problem} by design. We also provide a feasible retraction-based learning algorithm for HQMMs using constrained gradient descent on the Stiefel manifold of model parameters. We demonstrate that this approach is faster and scales to larger models than previous learning algorithms.
2019-12-01
ArXiv (preprint)
arxiv.org
arxiv.org
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng
Remi Tachet des Combes
Byron Boots
Geoff Gordon
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (see more)any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any
2019-11-01
ArXiv (preprint)
arxiv.org
arxiv.org
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Mariya Toneva*
Alessandro Sordoni
Remi Tachet des Combes
Adam Trischler
Yoshua Bengio
Geoff Gordon
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single class… (see more)ification tasks. Our goal is to understand whether a related phenomenon occurs when data does not undergo a clear distributional shift. We define a “forgetting event” to have occurred when an individual training example transitions from being classified correctly to incorrectly over the course of learning. Across several benchmark data sets, we find that: (i) certain examples are forgotten with high frequency, and some not at all; (ii) a data set’s (un)forgettable examples generalize across neural architectures; and (iii) based on forgetting dynamics, a significant fraction of examples can be omitted from the training data set while still maintaining state-of-the-art generalization performance.
2019-01-01
ICLR.cc/2019/Conference (poster)
openreview.net
openreview.net