Bayesian Deep Learning and a Probabilistic Perspective of Generalization

Mar 17, 2020
Andrew Gordon Wilson, Pavel Izmailov

* 28 pages, 17 figures 

  Access Model/Code and Paper
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited

Mar 04, 2020
Wesley J. Maddox, Gregory Benton, Andrew Gordon Wilson


  Access Model/Code and Paper
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data

Feb 25, 2020
Marc Finzi, Samuel Stanton, Pavel Izmailov, Andrew Gordon Wilson


  Access Model/Code and Paper
The Case for Bayesian Deep Learning

Jan 29, 2020
Andrew Gordon Wilson


  Access Model/Code and Paper
Semi-Supervised Learning with Normalizing Flows

Dec 30, 2019
Pavel Izmailov, Polina Kirichenko, Marc Finzi, Andrew Gordon Wilson


  Access Model/Code and Paper
Randomly Projected Additive Gaussian Processes for Regression

Dec 30, 2019
Ian A. Delbridge, David S. Bindel, Andrew Gordon Wilson


  Access Model/Code and Paper
Function-Space Distributions over Kernels

Oct 29, 2019
Gregory W. Benton, Wesley J. Maddox, Jayson P. Salkey, Julio Albinati, Andrew Gordon Wilson

* Published at NeurIPS 2019 

  Access Model/Code and Paper
BoTorch: Programmable Bayesian Optimization in PyTorch

Oct 14, 2019
Maximilian Balandat, Brian Karrer, Daniel R. Jiang, Samuel Daulton, Benjamin Letham, Andrew Gordon Wilson, Eytan Bakshy


  Access Model/Code and Paper
Subspace Inference for Bayesian Deep Learning

Jul 17, 2019
Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson

* Published at UAI 2019 

  Access Model/Code and Paper
SWALP : Stochastic Weight Averaging in Low-Precision Training

May 20, 2019
Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa

* Published at ICML 2019 

  Access Model/Code and Paper
Simple Black-box Adversarial Attacks

May 17, 2019
Chuan Guo, Jacob R. Gardner, Yurong You, Andrew Gordon Wilson, Kilian Q. Weinberger

* Published at ICML 2019 

  Access Model/Code and Paper
SysML: The New Frontier of Machine Learning Systems

May 01, 2019
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar


  Access Model/Code and Paper
Exact Gaussian Processes on a Million Data Points

Mar 19, 2019
Ke Alexander Wang, Geoff Pleiss, Jacob R. Gardner, Stephen Tyree, Kilian Q. Weinberger, Andrew Gordon Wilson


  Access Model/Code and Paper
Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning

Mar 12, 2019
Jian Wu, Saul Toscano-Palmerin, Peter I. Frazier, Andrew Gordon Wilson


  Access Model/Code and Paper
Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

Feb 11, 2019
Ruqi Zhang, Chunyuan Li, Jianyi Zhang, Changyou Chen, Andrew Gordon Wilson


  Access Model/Code and Paper
A Simple Baseline for Bayesian Uncertainty in Deep Learning

Feb 07, 2019
Wesley Maddox, Timur Garipov, Pavel Izmailov, Dmitry Vetrov, Andrew Gordon Wilson


  Access Model/Code and Paper
Change Surfaces for Expressive Multidimensional Changepoints and Counterfactual Prediction

Oct 30, 2018
William Herlands, Daniel B. Neill, Hannes Nickisch, Andrew Gordon Wilson


  Access Model/Code and Paper
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Oct 30, 2018
Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry Vetrov, Andrew Gordon Wilson

* Appears at Advances in Neural Information Processing Systems (NIPS), 2018 

  Access Model/Code and Paper
Scaling Gaussian Process Regression with Derivatives

Oct 29, 2018
David Eriksson, Kun Dong, Eric Hans Lee, David Bindel, Andrew Gordon Wilson

* Advances in Neural Information Processing Systems 32 (NIPS), 2018 
* Appears at Advances in Neural Information Processing Systems 32 (NIPS), 2018 

  Access Model/Code and Paper
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration

Oct 29, 2018
Jacob R. Gardner, Geoff Pleiss, David Bindel, Kilian Q. Weinberger, Andrew Gordon Wilson

* NIPS 2018 

  Access Model/Code and Paper
Averaging Weights Leads to Wider Optima and Better Generalization

Aug 08, 2018
Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson

* Appears at the Conference on Uncertainty in Artificial Intelligence (UAI), 2018 

  Access Model/Code and Paper
Constant-Time Predictive Distributions for Gaussian Processes

Jun 20, 2018
Geoff Pleiss, Jacob R. Gardner, Kilian Q. Weinberger, Andrew Gordon Wilson

* ICML 2018 

  Access Model/Code and Paper
Improving Consistency-Based Semi-Supervised Learning with Weight Averaging

Jun 19, 2018
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

* Fixed a typo for the direction of inequality for $C(\alpha)$ in 3.2 

  Access Model/Code and Paper
Probabilistic FastText for Multi-Sense Word Embeddings

Jun 07, 2018
Ben Athiwaratkun, Andrew Gordon Wilson, Anima Anandkumar

* Published at ACL 2018 

  Access Model/Code and Paper
Hierarchical Density Order Embeddings

Apr 26, 2018
Ben Athiwaratkun, Andrew Gordon Wilson

* Published at ICLR 2018 

  Access Model/Code and Paper
Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data

Apr 04, 2018
William Herlands, Edward McFowland III, Andrew Gordon Wilson, Daniel B. Neill

* Presented at AISTATS 2018. 11 pages. Supplement to main paper is included here as an appendix 

  Access Model/Code and Paper
Product Kernel Interpolation for Scalable Gaussian Processes

Feb 24, 2018
Jacob R. Gardner, Geoff Pleiss, Ruihan Wu, Kilian Q. Weinberger, Andrew Gordon Wilson

* Appears in Artificial Intelligence and Statistics (AISTATS) 21, 2018 

  Access Model/Code and Paper
Bayesian Optimization with Gradients

Feb 07, 2018
Jian Wu, Matthias Poloczek, Andrew Gordon Wilson, Peter I. Frazier

* Advances in Neural Information Processing Systems 30 (NIPS), 2017 
* Advances in Neural Information Processing Systems 30 (NIPS), 2017 

  Access Model/Code and Paper