Yarin Gal

Affiliations:
  • University of Oxford, Department of Computer Science, UK
  • Alan Turing Institute, London, UK


According to our database1, Yarin Gal authored at least 137 papers between 2010 and 2022.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2022
Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference.
IEEE Trans. Medical Imaging, 2022

Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation.
CoRR, 2022

Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities.
CoRR, 2022

Plex: Towards Reliability using Pretrained Large Model Extensions.
CoRR, 2022

Learning Dynamics and Generalization in Reinforcement Learning.
CoRR, 2022

Global geomagnetic perturbation forecasting using Deep Learning.
CoRR, 2022

Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling.
CoRR, 2022

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions.
CoRR, 2022

Interventions, Where and How? Experimental Design for Causal Models at Scale.
CoRR, 2022

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation.
CoRR, 2022

A Note on "Assessing Generalization of SGD via Disagreement".
CoRR, 2022

Continual Learning via Sequential Function-Space Variational Inference.
Proceedings of the International Conference on Machine Learning, 2022

Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval.
Proceedings of the International Conference on Machine Learning, 2022

Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt.
Proceedings of the International Conference on Machine Learning, 2022

Learning Dynamics and Generalization in Deep Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2022

KL Guided Domain Adaptation.
Proceedings of the Tenth International Conference on Learning Representations, 2022

GeneDisco: A Benchmark for Experimental Design in Drug Discovery.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning.
J. Mach. Learn. Res., 2021

DARTS without a Validation Set: Optimizing the Marginal Likelihood.
CoRR, 2021

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Metrics and Benchmarking Results.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
CoRR, 2021

Decomposing Representations for Deterministic Uncertainty Estimation.
CoRR, 2021

DeDUCE: Generating Counterfactual Explanations Efficiently.
CoRR, 2021

Contrastive Representation Learning with Trainable Augmentation Channel.
CoRR, 2021

Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation.
CoRR, 2021

Deep Deterministic Uncertainty for Semantic Segmentation.
CoRR, 2021

Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific.
CoRR, 2021

Quantifying Uncertainty for Machine Learning Based Diagnostic.
CoRR, 2021

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks.
CoRR, 2021

Prioritized training on points that are learnable, worth learning, and not yet learned.
CoRR, 2021

A Practical & Unified Notation for Information-Theoretic Quantities in ML.
CoRR, 2021

A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions.
CoRR, 2021

Active Learning under Pool Set Distribution Shift and Noisy Data.
CoRR, 2021

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning.
CoRR, 2021

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective.
CoRR, 2021

Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization.
CoRR, 2021

Robustness to Pruning Predicts Generalization in Deep Neural Networks.
CoRR, 2021

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty.
CoRR, 2021

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression.
CoRR, 2021

Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition.
CoRR, 2021

Technology Readiness Levels for Machine Learning Systems.
CoRR, 2021

Evaluating Approximate Inference in Bayesian Deep Learning.
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Outcome-Driven Reinforcement Learning via Variational Inference.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Speedy Performance Estimation for Neural Architecture Search.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving black-box optimization in VAE latent space using decoder uncertainty.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Domain Invariant Representation Learning with Domain Density Transformations.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes.
Proceedings of the 38th International Conference on Machine Learning, 2021

Active Testing: Sample-Efficient Model Evaluation.
Proceedings of the 38th International Conference on Machine Learning, 2021

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding.
Proceedings of the 38th International Conference on Machine Learning, 2021

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

On Statistical Bias In Active Learning: How and When to Fix It.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learning Invariant Representations for Reinforcement Learning without Reconstruction.
Proceedings of the 9th International Conference on Learning Representations, 2021

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Conditional BRUNO: A neural process for exchangeable labelled data.
Neurocomputing, 2020

Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning.
CoRR, 2020

On Batch Normalisation for Approximate Bayesian Inference.
CoRR, 2020

Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders.
CoRR, 2020

A Bayesian Perspective on Training Speed and Model Selection.
CoRR, 2020

Physics-informed GANs for Coastal Flood Visualization.
CoRR, 2020

Interlocking Backpropagation: Improving depthwise model-parallelism.
CoRR, 2020

On the robustness of effectiveness estimation of nonpharmaceutical interventions against COVID-19 transmission.
CoRR, 2020

SliceOut: Training Transformers and CNNs faster while using less memory.
CoRR, 2020

Single Shot Structured Pruning Before Training.
CoRR, 2020

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers.
CoRR, 2020

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search.
CoRR, 2020

Uncertainty Evaluation Metric for Brain Tumour Segmentation.
CoRR, 2020

On the Benefits of Invariance in Neural Networks.
CoRR, 2020

Capsule Networks - A Probabilistic Perspective.
CoRR, 2020

Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning.
CoRR, 2020

Baryons from Mesons: A Machine Learning Perspective.
CoRR, 2020

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network.
CoRR, 2020

Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks.
CoRR, 2020

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Bayesian Perspective on Training Speed and Model Selection.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Model and Data Uncertainty for Satellite Time Series Forecasting with Deep Recurrent Models.
Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, 2020

Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Inter-domain Deep Gaussian Processes.
Proceedings of the 37th International Conference on Machine Learning, 2020

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Proceedings of the 37th International Conference on Machine Learning, 2020

Uncertainty Estimation Using a Single Deep Deterministic Neural Network.
Proceedings of the 37th International Conference on Machine Learning, 2020

Invariant Causal Prediction for Block MDPs.
Proceedings of the 37th International Conference on Machine Learning, 2020

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

BayesOpt Adversarial Attack.
Proceedings of the 8th International Conference on Learning Representations, 2020

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks.
CoRR, 2019

Adversarial recovery of agent rewards from latent spaces of the limit order book.
CoRR, 2019

Auto-Calibration of Remote Sensing Solar Telescopes with Deep Learning.
CoRR, 2019

Using U-Nets to Create High-Fidelity Virtual Observations of the Solar Corona.
CoRR, 2019

Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics \& Losses.
CoRR, 2019

Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties.
CoRR, 2019

Machine Learning for Generalizable Prediction of Flood Susceptibility.
CoRR, 2019

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder.
CoRR, 2019

Flood Detection On Low Cost Orbital Hardware.
CoRR, 2019

Prediction of GNSS Phase Scintillations: A Machine Learning Approach.
CoRR, 2019

Generalizing from a few environments in safety-critical reinforcement learning.
CoRR, 2019

Radial Bayesian Neural Networks: Robust Variational Inference In Big Models.
CoRR, 2019

Towards Inverse Reinforcement Learning for Limit Order Book Dynamics.
CoRR, 2019

Learning Sparse Networks Using Targeted Dropout.
CoRR, 2019

An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval.
CoRR, 2019

Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning.
CoRR, 2019

Differentially Private Continual Learning.
CoRR, 2019

A Unifying Bayesian View of Continual Learning.
CoRR, 2019

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

An Empirical study of Binary Neural Networks' Optimisation.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
Evaluating Bayesian Deep Learning Methods for Semantic Segmentation.
CoRR, 2018

On the Importance of Strong Baselines in Bayesian Deep Learning.
CoRR, 2018

Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control.
CoRR, 2018

Idealised Bayesian Neural Networks Cannot Have Adversarial Examples: Theoretical and Empirical Study.
CoRR, 2018

Towards Robust Evaluations of Continual Learning.
CoRR, 2018

Loss-Calibrated Approximate Inference in Bayesian Neural Networks.
CoRR, 2018

Understanding Measures of Uncertainty for Adversarial Example Detection.
Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018

BRUNO: A Deep Recurrent Model for Exchangeable Data.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam.
Proceedings of the 35th International Conference on Machine Learning, 2018

Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017
Vprop: Variational Inference using RMSprop.
CoRR, 2017

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Concrete Dropout.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Real Time Image Saliency for Black Box Classifiers.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Dropout Inference in Bayesian Neural Networks with Alpha-divergences.
Proceedings of the 34th International Conference on Machine Learning, 2017

Deep Bayesian Active Learning with Image Data.
Proceedings of the 34th International Conference on Machine Learning, 2017

2016
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning.
Proceedings of the 33nd International Conference on Machine Learning, 2016

2015
Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference.
CoRR, 2015

Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data.
Proceedings of the 32nd International Conference on Machine Learning, 2015

2014
Semantics, Modelling, and the Problem of Representation of Meaning - a Brief Survey of Recent Literature.
CoRR, 2014

Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Pitfalls in the use of Parallel Inference for the Dirichlet Process.
Proceedings of the 31th International Conference on Machine Learning, 2014

2013
A Systematic Bayesian Treatment of the IBM Alignment Models.
Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, 2013

2010
Overcoming Alpha-Beta Limitations Using Evolved Artificial Neural Networks.
Proceedings of the Ninth International Conference on Machine Learning and Applications, 2010


  Loading...