Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.
Relational learning via collective matrix factorization
This model generalizes several existing matrix factorization methods, and therefore yields new large-scale optimization algorithms for these problems, which can handle any pairwise relational schema and a wide variety of error models.
Stable Function Approximation in Dynamic Programming
- Geoffrey J. Gordon
- Computer Science, MathematicsICML
ARA*: Anytime A* with Provable Bounds on Sub-Optimality
An anytime heuristic search, ARA*, is proposed, which tunes its performance bound based on available search time, and starts by finding a suboptimal solution quickly using a loose bound, then tightens the bound progressively as time allows.
Adversarial Multiple Source Domain Adaptation
- H. Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, J. Costeira, Geoffrey J. Gordon
- Computer ScienceNeurIPS
This paper proposes multisource domain adversarial networks (MDAN) that approach domain adaptation by optimizing task-adaptive generalization bounds and conducts extensive experiments showing superior adaptation performance on both classification and regression problems: sentiment analysis, digit classification, and vehicle counting.
Automatic Database Management System Tuning Through Large-scale Machine Learning
- Dana Van Aken, Andrew Pavlo, Geoffrey J. Gordon, Bohan Zhang
- Computer ScienceSIGMOD Conference
- 9 May 2017
An automated approach that leverages past experience and collects new information to tune DBMS configurations and recommends configurations that are as good as or better than ones generated by existing tools or a human expert is presented.
Anytime Point-Based Approximations for Large POMDPs
The point selection procedure is combined with point-based value backups to form an effective anytime POMDP algorithm called Point-Based Value Iteration (PBVI), and a theoretical analysis justifying the choice of belief selection technique is presented.
On Learning Invariant Representations for Domain Adaptation
This paper constructs a simple counterexample showing that, contrary to common belief, the above conditions are not sufficient to guarantee successful domain adaptation, and proposes a natural and interpretable generalization upper bound that explicitly takes into account the aforementioned shift.
An Empirical Study of Example Forgetting during Deep Neural Network Learning
- Mariya Toneva, Alessandro Sordoni, Rémi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon
- Computer ScienceICLR
- 27 September 2018
It is found that certain examples are forgotten with high frequency, and some not at all; a data set’s (un)forgettable examples generalize across neural architectures; and a significant fraction of examples can be omitted from the training data set while still maintaining state-of-the-art generalization performance.
Individualized Bayesian Knowledge Tracing Models
It is shown that student-specific parameters lead to a tangible improvement when predicting the data of unseen students, and that parameterizing students’ speed of learning is more beneficial than parameterizing a priori knowledge.