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 Oscar Key

Oscar Key
Alert button

Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference


Jan 30, 2023
Ayush Bharti, Masha Naslidnyk, Oscar Key, Samuel Kaski, François-Xavier Briol

Add code
Alert button

Figure 1 for Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
Figure 2 for Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
Figure 3 for Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
Figure 4 for Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Healing the Blindness of Score Matching


Sep 15, 2022
Mingtian Zhang, Oscar Key, Peter Hayes, David Barber, Brooks Paige, François-Xavier Briol

Add code
Alert button

Figure 1 for Towards Healing the Blindness of Score Matching
Figure 2 for Towards Healing the Blindness of Score Matching
Figure 3 for Towards Healing the Blindness of Score Matching
Figure 4 for Towards Healing the Blindness of Score Matching

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Composite Goodness-of-fit Tests with Kernels


Nov 19, 2021
Oscar Key, Tamara Fernandez, Arthur Gretton, François-Xavier Briol

Add code
Alert button

Figure 1 for Composite Goodness-of-fit Tests with Kernels
Figure 2 for Composite Goodness-of-fit Tests with Kernels

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties


Mar 16, 2021
Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal

Add code
Alert button

Figure 1 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 2 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 3 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 4 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
* Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021 
 * 21 pages, 13 Figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression


Feb 22, 2021
Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal

Add code
Alert button

Figure 1 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 2 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 3 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 4 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes


Nov 01, 2020
Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth

Add code
Alert button

Figure 1 for On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
Figure 2 for On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
Figure 3 for On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
Figure 4 for On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Interlocking Backpropagation: Improving depthwise model-parallelism


Oct 08, 2020
Aidan N. Gomez, Oscar Key, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal

Add code
Alert button

Figure 1 for Interlocking Backpropagation: Improving depthwise model-parallelism
Figure 2 for Interlocking Backpropagation: Improving depthwise model-parallelism
Figure 3 for Interlocking Backpropagation: Improving depthwise model-parallelism
Figure 4 for Interlocking Backpropagation: Improving depthwise model-parallelism

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email