Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Andrew Gordon Wilson

Andrew Gordon Wilson

Bayesian Optimization with High-Dimensional Outputs


Jun 24, 2021
Wesley J. Maddox, Maximilian Balandat, Andrew Gordon Wilson, Eytan Bakshy

Figure 1 for Bayesian Optimization with High-Dimensional Outputs
Figure 2 for Bayesian Optimization with High-Dimensional Outputs
Figure 3 for Bayesian Optimization with High-Dimensional Outputs
Figure 4 for Bayesian Optimization with High-Dimensional Outputs

  Access Paper or Ask Questions

Task-agnostic Continual Learning with Hybrid Probabilistic Models


Jun 24, 2021
Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu

Figure 1 for Task-agnostic Continual Learning with Hybrid Probabilistic Models
Figure 2 for Task-agnostic Continual Learning with Hybrid Probabilistic Models
Figure 3 for Task-agnostic Continual Learning with Hybrid Probabilistic Models
Figure 4 for Task-agnostic Continual Learning with Hybrid Probabilistic Models

  Access Paper or Ask Questions

Dangers of Bayesian Model Averaging under Covariate Shift


Jun 22, 2021
Pavel Izmailov, Patrick Nicholson, Sanae Lotfi, Andrew Gordon Wilson

Figure 1 for Dangers of Bayesian Model Averaging under Covariate Shift
Figure 2 for Dangers of Bayesian Model Averaging under Covariate Shift
Figure 3 for Dangers of Bayesian Model Averaging under Covariate Shift
Figure 4 for Dangers of Bayesian Model Averaging under Covariate Shift

  Access Paper or Ask Questions

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes


Jun 12, 2021
Sanyam Kapoor, Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson

Figure 1 for SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Figure 2 for SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Figure 3 for SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Figure 4 for SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
* International Conference on Machine Learning (ICML), 2021 
  Access Paper or Ask Questions

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition


Jun 10, 2021
Shengyang Sun, Jiaxin Shi, Andrew Gordon Wilson, Roger Grosse

Figure 1 for Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Figure 2 for Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Figure 3 for Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Figure 4 for Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
* ICML2021, 21 pages 
  Access Paper or Ask Questions

Does Knowledge Distillation Really Work?


Jun 10, 2021
Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A. Alemi, Andrew Gordon Wilson

Figure 1 for Does Knowledge Distillation Really Work?
Figure 2 for Does Knowledge Distillation Really Work?
Figure 3 for Does Knowledge Distillation Really Work?
Figure 4 for Does Knowledge Distillation Really Work?

  Access Paper or Ask Questions

What Are Bayesian Neural Network Posteriors Really Like?


Apr 29, 2021
Pavel Izmailov, Sharad Vikram, Matthew D. Hoffman, Andrew Gordon Wilson

Figure 1 for What Are Bayesian Neural Network Posteriors Really Like?
Figure 2 for What Are Bayesian Neural Network Posteriors Really Like?
Figure 3 for What Are Bayesian Neural Network Posteriors Really Like?
Figure 4 for What Are Bayesian Neural Network Posteriors Really Like?

  Access Paper or Ask Questions

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups


Apr 19, 2021
Marc Finzi, Max Welling, Andrew Gordon Wilson

Figure 1 for A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Figure 2 for A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Figure 3 for A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Figure 4 for A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
* Library: https://github.com/mfinzi/equivariant-MLP, Documentation: https://emlp.readthedocs.io/en/latest/, Examples: https://colab.research.google.com/github/mfinzi/equivariant-MLP/blob/master/docs/notebooks/colabs/all.ipynb 
  Access Paper or Ask Questions

Kernel Interpolation for Scalable Online Gaussian Processes


Mar 02, 2021
Samuel Stanton, Wesley J. Maddox, Ian Delbridge, Andrew Gordon Wilson

Figure 1 for Kernel Interpolation for Scalable Online Gaussian Processes
Figure 2 for Kernel Interpolation for Scalable Online Gaussian Processes
Figure 3 for Kernel Interpolation for Scalable Online Gaussian Processes
Figure 4 for Kernel Interpolation for Scalable Online Gaussian Processes
* AISTATS 2021 
  Access Paper or Ask Questions

Fast Adaptation with Linearized Neural Networks


Mar 02, 2021
Wesley J. Maddox, Shuai Tang, Pablo Garcia Moreno, Andrew Gordon Wilson, Andreas Damianou

Figure 1 for Fast Adaptation with Linearized Neural Networks
Figure 2 for Fast Adaptation with Linearized Neural Networks
Figure 3 for Fast Adaptation with Linearized Neural Networks
Figure 4 for Fast Adaptation with Linearized Neural Networks
* AISTATS 2021 
  Access Paper or Ask Questions

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling


Feb 25, 2021
Gregory W. Benton, Wesley J. Maddox, Sanae Lotfi, Andrew Gordon Wilson

Figure 1 for Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Figure 2 for Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Figure 3 for Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Figure 4 for Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

  Access Paper or Ask Questions

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints


Oct 26, 2020
Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson

Figure 1 for Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
Figure 2 for Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
Figure 3 for Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
Figure 4 for Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
* NeurIPS 2020. Code available at https://github.com/mfinzi/constrained-hamiltonian-neural-networks 
  Access Paper or Ask Questions

Learning Invariances in Neural Networks


Oct 22, 2020
Gregory Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

Figure 1 for Learning Invariances in Neural Networks
Figure 2 for Learning Invariances in Neural Networks
Figure 3 for Learning Invariances in Neural Networks
Figure 4 for Learning Invariances in Neural Networks
* NeurIPS 2020. Code available at https://github.com/g-benton/learning-invariances 
  Access Paper or Ask Questions

On the model-based stochastic value gradient for continuous reinforcement learning


Aug 28, 2020
Brandon Amos, Samuel Stanton, Denis Yarats, Andrew Gordon Wilson

Figure 1 for On the model-based stochastic value gradient for continuous reinforcement learning
Figure 2 for On the model-based stochastic value gradient for continuous reinforcement learning
Figure 3 for On the model-based stochastic value gradient for continuous reinforcement learning
Figure 4 for On the model-based stochastic value gradient for continuous reinforcement learning

  Access Paper or Ask Questions

Improving GAN Training with Probability Ratio Clipping and Sample Reweighting


Jun 30, 2020
Yue Wu, Pan Zhou, Andrew Gordon Wilson, Eric P. Xing, Zhiting Hu

Figure 1 for Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Figure 2 for Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Figure 3 for Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Figure 4 for Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
* Fixed typos. Code available at: https://github.com/Holmeswww/PPOGAN 
  Access Paper or Ask Questions

Why Normalizing Flows Fail to Detect Out-of-Distribution Data


Jun 15, 2020
Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

Figure 1 for Why Normalizing Flows Fail to Detect Out-of-Distribution Data
Figure 2 for Why Normalizing Flows Fail to Detect Out-of-Distribution Data
Figure 3 for Why Normalizing Flows Fail to Detect Out-of-Distribution Data
Figure 4 for Why Normalizing Flows Fail to Detect Out-of-Distribution Data
* Code is available at https://github.com/PolinaKirichenko/flows_ood 
  Access Paper or Ask Questions

Bayesian Deep Learning and a Probabilistic Perspective of Generalization


Mar 17, 2020
Andrew Gordon Wilson, Pavel Izmailov

Figure 1 for Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Figure 2 for Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Figure 3 for Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Figure 4 for Bayesian Deep Learning and a Probabilistic Perspective of Generalization
* 28 pages, 17 figures 
  Access Paper or Ask Questions

Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited


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

Figure 1 for Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Figure 2 for Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Figure 3 for Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Figure 4 for Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited

  Access Paper or Ask Questions

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

Figure 1 for Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Figure 2 for Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Figure 3 for Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Figure 4 for Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data

  Access Paper or Ask Questions

The Case for Bayesian Deep Learning


Jan 29, 2020
Andrew Gordon Wilson


  Access Paper or Ask Questions

Semi-Supervised Learning with Normalizing Flows


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

Figure 1 for Semi-Supervised Learning with Normalizing Flows
Figure 2 for Semi-Supervised Learning with Normalizing Flows
Figure 3 for Semi-Supervised Learning with Normalizing Flows
Figure 4 for Semi-Supervised Learning with Normalizing Flows

  Access Paper or Ask Questions

Randomly Projected Additive Gaussian Processes for Regression


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

Figure 1 for Randomly Projected Additive Gaussian Processes for Regression
Figure 2 for Randomly Projected Additive Gaussian Processes for Regression
Figure 3 for Randomly Projected Additive Gaussian Processes for Regression
Figure 4 for Randomly Projected Additive Gaussian Processes for Regression

  Access Paper or Ask Questions

Function-Space Distributions over Kernels


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

Figure 1 for Function-Space Distributions over Kernels
Figure 2 for Function-Space Distributions over Kernels
Figure 3 for Function-Space Distributions over Kernels
Figure 4 for Function-Space Distributions over Kernels
* Published at NeurIPS 2019 
  Access Paper or Ask Questions

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

Figure 1 for BoTorch: Programmable Bayesian Optimization in PyTorch
Figure 2 for BoTorch: Programmable Bayesian Optimization in PyTorch
Figure 3 for BoTorch: Programmable Bayesian Optimization in PyTorch
Figure 4 for BoTorch: Programmable Bayesian Optimization in PyTorch

  Access Paper or Ask Questions

Subspace Inference for Bayesian Deep Learning


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

Figure 1 for Subspace Inference for Bayesian Deep Learning
Figure 2 for Subspace Inference for Bayesian Deep Learning
Figure 3 for Subspace Inference for Bayesian Deep Learning
Figure 4 for Subspace Inference for Bayesian Deep Learning
* Published at UAI 2019 
  Access Paper or Ask Questions

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

Figure 1 for SWALP : Stochastic Weight Averaging in Low-Precision Training
Figure 2 for SWALP : Stochastic Weight Averaging in Low-Precision Training
Figure 3 for SWALP : Stochastic Weight Averaging in Low-Precision Training
Figure 4 for SWALP : Stochastic Weight Averaging in Low-Precision Training
* Published at ICML 2019 
  Access Paper or Ask Questions

Simple Black-box Adversarial Attacks


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

Figure 1 for Simple Black-box Adversarial Attacks
Figure 2 for Simple Black-box Adversarial Attacks
Figure 3 for Simple Black-box Adversarial Attacks
Figure 4 for Simple Black-box Adversarial Attacks
* Published at ICML 2019 
  Access Paper or Ask Questions

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 Paper or Ask Questions