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 Yarin Gal

Yarin Gal

Quantifying Uncertainty for Machine Learning Based Diagnostic


Jul 29, 2021
Owen Convery, Lewis Smith, Yarin Gal, Adi Hanuka

Figure 1 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 2 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 3 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 4 for Quantifying Uncertainty for Machine Learning Based Diagnostic
* arXiv admin note: substantial text overlap with arXiv:2105.04654 
  Access Paper or Ask Questions

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks


Jul 23, 2021
Andrey Malinin, Neil Band, Ganshin, Alexander, German Chesnokov, Yarin Gal, Mark J. F. Gales, Alexey Noskov, Andrey Ploskonosov, Liudmila Prokhorenkova, Ivan Provilkov, Vatsal Raina, Vyas Raina, Roginskiy, Denis, Mariya Shmatova, Panos Tigas, Boris Yangel

Figure 1 for Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Figure 2 for Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Figure 3 for Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Figure 4 for Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

  Access Paper or Ask Questions

Prioritized training on points that are learnable, worth learning, and not yet learned


Jul 06, 2021
Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, Yarin Gal

Figure 1 for Prioritized training on points that are learnable, worth learning, and not yet learned
Figure 2 for Prioritized training on points that are learnable, worth learning, and not yet learned
Figure 3 for Prioritized training on points that are learnable, worth learning, and not yet learned
Figure 4 for Prioritized training on points that are learnable, worth learning, and not yet learned
* ICML 2021 Workshop on Subset Selection in Machine Learning 
  Access Paper or Ask Questions

Improving black-box optimization in VAE latent space using decoder uncertainty


Jun 30, 2021
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal

Figure 1 for Improving black-box optimization in VAE latent space using decoder uncertainty
Figure 2 for Improving black-box optimization in VAE latent space using decoder uncertainty
Figure 3 for Improving black-box optimization in VAE latent space using decoder uncertainty
Figure 4 for Improving black-box optimization in VAE latent space using decoder uncertainty

  Access Paper or Ask Questions

A Practical & Unified Notation for Information-Theoretic Quantities in ML


Jun 22, 2021
Andreas Kirsch, Yarin Gal

Figure 1 for A Practical & Unified Notation for Information-Theoretic Quantities in ML
Figure 2 for A Practical & Unified Notation for Information-Theoretic Quantities in ML
Figure 3 for A Practical & Unified Notation for Information-Theoretic Quantities in ML
Figure 4 for A Practical & Unified Notation for Information-Theoretic Quantities in ML

  Access Paper or Ask Questions

A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions


Jun 22, 2021
Andreas Kirsch, Sebastian Farquhar, Yarin Gal

Figure 1 for A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions
Figure 2 for A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions
Figure 3 for A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions

  Access Paper or Ask Questions

Active Learning under Pool Set Distribution Shift and Noisy Data


Jun 22, 2021
Andreas Kirsch, Tom Rainforth, Yarin Gal

Figure 1 for Active Learning under Pool Set Distribution Shift and Noisy Data
Figure 2 for Active Learning under Pool Set Distribution Shift and Noisy Data
Figure 3 for Active Learning under Pool Set Distribution Shift and Noisy Data
Figure 4 for Active Learning under Pool Set Distribution Shift and Noisy Data

  Access Paper or Ask Questions

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective


Jun 17, 2021
Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal

Figure 1 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 2 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 3 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 4 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
* Main paper 10 pages including references, appendix 10 pages. 7 figures and 6 tables including appendix 
  Access Paper or Ask Questions

KL Guided Domain Adaptation


Jun 14, 2021
A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip H. S. Torr, Atılım Güneş Baydin

Figure 1 for KL Guided Domain Adaptation
Figure 2 for KL Guided Domain Adaptation
Figure 3 for KL Guided Domain Adaptation
Figure 4 for KL Guided Domain Adaptation

  Access Paper or Ask Questions

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning


Jun 07, 2021
Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran

Figure 1 for Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Figure 2 for Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Figure 3 for Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Figure 4 for Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

  Access Paper or Ask Questions

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning


Jun 04, 2021
Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Tom Rainforth, Yarin Gal

Figure 1 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 2 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 3 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 4 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
* First two authors contributed equally 
  Access Paper or Ask Questions

Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization


May 05, 2021
Björn Lütjens, Brandon Leshchinskiy, Christian Requena-Mesa, Farrukh Chishtie, Natalia Díaz-Rodríguez, Océane Boulais, Aruna Sankaranarayanan, Aaron Piña, Yarin Gal, Chedy Raïssi, Alexander Lavin, Dava Newman

Figure 1 for Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization
Figure 2 for Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization
Figure 3 for Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization
Figure 4 for Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization
* arXiv admin note: text overlap with arXiv:2010.08103 
  Access Paper or Ask Questions

Outcome-Driven Reinforcement Learning via Variational Inference


Apr 20, 2021
Tim G. J. Rudner, Vitchyr H. Pong, Rowan McAllister, Yarin Gal, Sergey Levine

Figure 1 for Outcome-Driven Reinforcement Learning via Variational Inference
Figure 2 for Outcome-Driven Reinforcement Learning via Variational Inference
Figure 3 for Outcome-Driven Reinforcement Learning via Variational Inference
Figure 4 for Outcome-Driven Reinforcement Learning via Variational Inference

  Access Paper or Ask Questions

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

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

Robustness to Pruning Predicts Generalization in Deep Neural Networks


Mar 10, 2021
Lorenz Kuhn, Clare Lyle, Aidan N. Gomez, Jonas Rothfuss, Yarin Gal

Figure 1 for Robustness to Pruning Predicts Generalization in Deep Neural Networks
Figure 2 for Robustness to Pruning Predicts Generalization in Deep Neural Networks
Figure 3 for Robustness to Pruning Predicts Generalization in Deep Neural Networks
Figure 4 for Robustness to Pruning Predicts Generalization in Deep Neural Networks

  Access Paper or Ask Questions

Active Testing: Sample-Efficient Model Evaluation


Mar 09, 2021
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth

Figure 1 for Active Testing: Sample-Efficient Model Evaluation
Figure 2 for Active Testing: Sample-Efficient Model Evaluation
Figure 3 for Active Testing: Sample-Efficient Model Evaluation
Figure 4 for Active Testing: Sample-Efficient Model Evaluation

  Access Paper or Ask Questions

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding


Mar 08, 2021
Andrew Jesson, Sören Mindermann, Yarin Gal, Uri Shalit

Figure 1 for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Figure 2 for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Figure 3 for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Figure 4 for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
* 18 pages, 5 figures, In review 
  Access Paper or Ask Questions

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning


Feb 24, 2021
Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar

Figure 1 for PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Figure 2 for PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Figure 3 for PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Figure 4 for PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

  Access Paper or Ask Questions

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty


Feb 23, 2021
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal

Figure 1 for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
Figure 2 for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
Figure 3 for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
Figure 4 for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

  Access Paper or Ask Questions

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

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

Domain Invariant Representation Learning with Domain Density Transformations


Feb 14, 2021
A. Tuan Nguyen, Toan Tran, Yarin Gal, Atılım Güneş Baydin

Figure 1 for Domain Invariant Representation Learning with Domain Density Transformations
Figure 2 for Domain Invariant Representation Learning with Domain Density Transformations
Figure 3 for Domain Invariant Representation Learning with Domain Density Transformations
Figure 4 for Domain Invariant Representation Learning with Domain Density Transformations

  Access Paper or Ask Questions

Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition


Feb 02, 2021
Panagiotis Tigas, Téo Bloch, Vishal Upendran, Banafsheh Ferdoushi, Mark C. M. Cheung, Siddha Ganju, Ryan M. McGranaghan, Yarin Gal, Asti Bhatt

Figure 1 for Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
Figure 2 for Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
Figure 3 for Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
Figure 4 for Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
* Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada 
  Access Paper or Ask Questions

Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning


Feb 01, 2021
Luiz F. G. dos Santos, Souvik Bose, Valentina Salvatelli, Brad Neuberg, Mark C. M. Cheung, Miho Janvier, Meng Jin, Yarin Gal, Paul Boerner, Atılım Güneş Baydin

Figure 1 for Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
Figure 2 for Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
Figure 3 for Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
Figure 4 for Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
* 12 pages, 7 figures, 8 tables. This is a pre-print of an article submitted and accepted by A&A Journal 
  Access Paper or Ask Questions

On Statistical Bias In Active Learning: How and When To Fix It


Jan 27, 2021
Sebastian Farquhar, Yarin Gal, Tom Rainforth

Figure 1 for On Statistical Bias In Active Learning: How and When To Fix It
Figure 2 for On Statistical Bias In Active Learning: How and When To Fix It
Figure 3 for On Statistical Bias In Active Learning: How and When To Fix It
Figure 4 for On Statistical Bias In Active Learning: How and When To Fix It
* Published at ICLR 2021 (Spotlight) 
  Access Paper or Ask Questions

Technology Readiness Levels for Machine Learning Systems


Jan 11, 2021
Alexander Lavin, Ciarán M. Gilligan-Lee, Alessya Visnjic, Siddha Ganju, Dava Newman, Sujoy Ganguly, Danny Lange, Atılım Güneş Baydin, Amit Sharma, Adam Gibson, Yarin Gal, Eric P. Xing, Chris Mattmann, James Parr

Figure 1 for Technology Readiness Levels for Machine Learning Systems
Figure 2 for Technology Readiness Levels for Machine Learning Systems

  Access Paper or Ask Questions