Publications

2016

The Variational Fair Autoencoder
Christos Louizos, Kevin Swersky, Yujia Li, Max Welling and Richard Zemel
International Conference on Learning Representations (ICLR 2016), Oral Presentation
[pdf]

Taking the Human Out of the Loop: A Review of Bayesian Optimization
Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams and Nando de Freitas
In Proceedings of the IEEE (Vol. 104, pp. 1–28)
[link]

2015

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
Jimmy Ba, Kevin Swersky, Sanja Fidler and Ruslan Salakhutdinov
International Conference on Computer Vision (ICCV 2015)
[pdf]

Scalable Bayesian Optimization Using Deep Neural Networks
Jasper Snoek, Oren Rippel, Kevin Swersky, Ryan Kiros, Nadathur Satish, Narayanan Sundaram, Md. Mostofa Ali Patwary, Prabhat and Ryan P. Adams
International Conference on Machine Learning (ICML 2015)
[pdf]

Generative Moment Matching Networks
Yujia Li, Kevin Swersky and Richard Zemel
International Conference on Machine Learning (ICML 2015)
[pdf]

2014

Freeze-Thaw Bayesian Optimization
Kevin Swersky, Jasper Snoek and Ryan Adams
[arXiv preprint]

Learning Unbiased Features
Yujia Li, Kevin Swersky and Richard Zemel
Neural Information Processing Systems Workshop on Transfer and Multi-Task Learning
[pdf]

Input Warping for Bayesian Optimization of Non-stationary Functions
Jasper Snoek, Kevin Swersky, Richard Zemel and Ryan Adams
International Conference on Machine Learning (ICML 2014)
[pdfarXiv preprint]

2013

Input Warping for Bayesian Optimization of Non-stationary Functions
Jasper Snoek, Kevin Swersky, Richard Zemel and Ryan Adams
Neural Information Processing Systems Workshop on Bayesian Optimization
[pdf]

Efficient Feature Learning using Perturb-and-MAP
Ke Li, Kevin Swersky, and Richard Zemel
Neural Information Processing Systems Workshop on Perturbations, Optimization, and Statistics
[pdf]

Raiders of the Lost ArchitectureKernels for Bayesian Optimization in Conditional Parameter Spaces
Kevin Swersky, David Duvenaud, Jasper Snoek, Frank Hutter and Michael Osborne
Neural Information Processing Systems Workshop on Bayesian Optimization
[pdf]

Multi-Task Bayesian Optimization.
Kevin Swersky, Jasper Snoek and Ryan Adams.
Neural Information Processing Systems (NIPS 2013).
[pdf, appendix]

Learning Fair Representations.
Richard Zemel, Yu (Ledell) Wu, Kevin Swersky, Toniann Pitassi and Cynthia Dwork.
International Conference on Machine Learning (ICML 2013).
[pdf, appendix]

Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning.
Daniel Tarlow, Kevin Swersky, Laurent Charlin, Ilya Sutskever and Richard Zemel.
International Conference on Machine Learning (ICML 2013).
[pdf, appendix]

2012

Probabilistic n-Choose-k Models for Classification and Ranking.
Kevin Swersky, Daniel Tarlow, Ryan Adams, Richard Zemel and Brendan Frey.
Neural Information Processing Systems (NIPS 2012).
[pdf, appendix, poster]

Cardinality Restricted Boltzmann Machines.
Kevin Swersky, Daniel Tarlow, Ilya Sutskever, Ruslan Salakhutdinov, Richard Zemel and Ryan Adams.
Neural Information Processing Systems (NIPS 2012).
[pdf, poster]

Fast Exact Inference for Recursive Cardinality Models.
Daniel Tarlow, Kevin Swersky, Richard Zemel, Ryan Adams and Brendan Frey.
Uncertainty in Artificial Intelligence (UAI 2012).
[pdf + appendix]

Estimating the Hessian by Backpropagating Curvature.
James Martens, Ilya Sutskever and Kevin Swersky.
International Conference on Machine Learning (ICML 2012).
[pdf, appendix]

Prediction and Fault Detection of Environmental Signals with Uncharacterised Faults.
Michael A. Osborne, Roman Garnett, Kevin Swersky and Nando de Freitas.
AAAI Conference on Artificial Intelligence (AAAI 2012).
[pdf, appendix, code]

2011

On Autoencoders and Score Matching for Energy Based Models.
Kevin Swersky, Marc’Aurelio Ranzato, David Buchman, Benjamin Marlin, and Nando de Freitas.
International Conference on Machine Learning (ICML 2011).
[pdf, appendixposter]

A Machine Learning Approach to Pattern Detection and Prediction for Environmental Monitoring and Water Sustainability.
Michael A. Osborne, Roman Garnett, Kevin Swersky and Nando de Freitas.
ICML 2011 Workshop on Machine Learning for Global Challenges.
[pdf]

2010

Inductive Principles for Restricted Boltzmann Machine Learning.
Benjamin Marlin, Kevin Swersky, Bo Chen and Nando de Freitas.
Artificial Intelligence and Statistics (AISTATS 2010).
[pdf, poster]

Inductive Principles for Learning Restricted Boltzmann Machines.
Kevin Swersky.
Master’s thesis, University of British Columbia.
[pdf]

A Tutorial on Stochastic Approximation Algorithms for Training Restricted Boltzmann Machines and Deep Belief Nets.
Kevin Swersky, Bo Chen, Benjamin Marlin, and Nando de Freitas.
Information Theory and Applications (ITA 2010) Workshop.
[pdf]

Sparsity Priors and Boosting for Learning Localized Distributed Feature Representations.
Bo Chen, Kevin Swersky, Benjamin Marlin and Nando de Freitas.
Technical Report TR-2010-04, University of British Columbia.
[pdf]