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

Transfer Learning with Deep Tabular Models



Roman Levin , Valeriia Cherepanova , Avi Schwarzschild , Arpit Bansal , C. Bayan Bruss , Tom Goldstein , Andrew Gordon Wilson , Micah Goldblum

Figure 1 for Transfer Learning with Deep Tabular Models
Figure 2 for Transfer Learning with Deep Tabular Models
Figure 3 for Transfer Learning with Deep Tabular Models
Figure 4 for Transfer Learning with Deep Tabular Models

   Access Paper or Ask Questions

Low-Precision Stochastic Gradient Langevin Dynamics



Ruqi Zhang , Andrew Gordon Wilson , Christopher De Sa

Figure 1 for Low-Precision Stochastic Gradient Langevin Dynamics
Figure 2 for Low-Precision Stochastic Gradient Langevin Dynamics
Figure 3 for Low-Precision Stochastic Gradient Langevin Dynamics
Figure 4 for Low-Precision Stochastic Gradient Langevin Dynamics
* Published at ICML 2022 
   Access Paper or Ask Questions

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors



Ravid Shwartz-Ziv , Micah Goldblum , Hossein Souri , Sanyam Kapoor , Chen Zhu , Yann LeCun , Andrew Gordon Wilson

Figure 1 for Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Figure 2 for Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Figure 3 for Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Figure 4 for Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
* Code available at https://github.com/hsouri/BayesianTransferLearning 
   Access Paper or Ask Questions

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations



Polina Kirichenko , Pavel Izmailov , Andrew Gordon Wilson

Figure 1 for Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Figure 2 for Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Figure 3 for Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Figure 4 for Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
* Code is available at https://github.com/PolinaKirichenko/deep_feature_reweighting 
   Access Paper or Ask Questions

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification



Sanyam Kapoor , Wesley J. Maddox , Pavel Izmailov , Andrew Gordon Wilson

Figure 1 for On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Figure 2 for On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Figure 3 for On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Figure 4 for On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification

   Access Paper or Ask Questions

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders



Samuel Stanton , Wesley Maddox , Nate Gruver , Phillip Maffettone , Emily Delaney , Peyton Greenside , Andrew Gordon Wilson

Figure 1 for Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
Figure 2 for Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
Figure 3 for Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
Figure 4 for Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

   Access Paper or Ask Questions

Bayesian Model Selection, the Marginal Likelihood, and Generalization



Sanae Lotfi , Pavel Izmailov , Gregory Benton , Micah Goldblum , Andrew Gordon Wilson

Figure 1 for Bayesian Model Selection, the Marginal Likelihood, and Generalization
Figure 2 for Bayesian Model Selection, the Marginal Likelihood, and Generalization
Figure 3 for Bayesian Model Selection, the Marginal Likelihood, and Generalization
Figure 4 for Bayesian Model Selection, the Marginal Likelihood, and Generalization

   Access Paper or Ask Questions

Deconstructing the Inductive Biases of Hamiltonian Neural Networks



Nate Gruver , Marc Finzi , Samuel Stanton , Andrew Gordon Wilson

Figure 1 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 2 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 3 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 4 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
* ICLR 2022. Code available at https://github.com/ngruver/decon-hnn 
   Access Paper or Ask Questions

When are Iterative Gaussian Processes Reliably Accurate?



Wesley J. Maddox , Sanyam Kapoor , Andrew Gordon Wilson

Figure 1 for When are Iterative Gaussian Processes Reliably Accurate?
Figure 2 for When are Iterative Gaussian Processes Reliably Accurate?
Figure 3 for When are Iterative Gaussian Processes Reliably Accurate?
Figure 4 for When are Iterative Gaussian Processes Reliably Accurate?
* ICML 2021 OPTML Workshop 
   Access Paper or Ask Questions

Residual Pathway Priors for Soft Equivariance Constraints



Marc Finzi , Gregory Benton , Andrew Gordon Wilson

Figure 1 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 2 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 3 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 4 for Residual Pathway Priors for Soft Equivariance Constraints
* NeurIPS 2021. Code available at https://github.com/mfinzi/residual-pathway-priors 
   Access Paper or Ask Questions
1
2
3
4
5
6
7
>>