Y. Gal

发表

Robust Imitative Planning: Planning from Demonstrations Under Uncertainty

S. Levine, Rowan McAllister, P. Tigas, 2019 .

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning pdf

Zoubin Ghahramani, Yarin Gal, Zoubin Ghahramani, 2015, ICML.

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

Zoubin Ghahramani, Yarin Gal, Zoubin Ghahramani, 2015, NIPS.

Invariant Causal Prediction for Block MDPs pdf

Joelle Pineau, Doina Precup, Yarin Gal, 2020, ICML.

Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning

Roberto Cipolla, Mark van der Wilk, Adrian Weller, 2017, IJCAI.

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference pdf

Zoubin Ghahramani, Yarin Gal, Zoubin Ghahramani, 2015, ArXiv.

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

Yee Whye Teh, Yarin Gal, Leonid Chindelevitch, 2020, NeurIPS.

The effectiveness and perceived burden of nonpharmaceutical interventions against COVID-19 transmission: a modelling study with 41 countries

Y. Teh, Y. Gal, J. Salvatier, 2020, medRxiv.

On the robustness of effectiveness estimation of nonpharmaceutical interventions against COVID-19 transmission pdf

Yee Whye Teh, Yarin Gal, Leonid Chindelevitch, 2020, ArXiv.

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Alex Kendall, Yarin Gal, Y. Gal, 2017, NIPS.

Baryons from Mesons: A Machine Learning Perspective pdf

Yarin Gal, Vishnu Jejjala, Damian Kaloni Mayorga Pena, 2020, ArXiv.

Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models

Carl E. Rasmussen, Mark van der Wilk, Yarin Gal, 2014, NIPS.

Deep Bayesian Active Learning with Image Data pdf

Zoubin Ghahramani, Yarin Gal, Riashat Islam, 2017, ICML.

Dropout as a Bayesian Approximation: Appendix

Zoubin Ghahramani, Yarin Gal, Zoubin Ghahramani, 2015, 1506.02157.

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

Yarin Gal, Andreas Kirsch, Joost van Amersfoort, 2019, NeurIPS.

Uncertainty in Deep Learning

Yarin Gal, Y. Gal, 2016 .

BRUNO: A Deep Recurrent Model for Exchangeable Data

Arthur Gretton, Jonas Degrave, Joni Dambre, 2018, NeurIPS.

Dropout Inference in Bayesian Neural Networks with Alpha-divergences

Yarin Gal, Yingzhen Li, Y. Gal, 2017, ICML.

Improving MFVI in Bayesian Neural Networks with Empirical Bayes: a Study with Diabetic Retinopathy Diagnosis

Angelos Filos, Y. Gal, O. Tickoo, 2019 .

Variational Inference for Sparse Spectrum Approximation in Gaussian Process Regression

Richard E. Turner, Y. Gal, 2015 .

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network

Joost R. van Amersfoort, Y. Teh, Y. Gal, 2020, ICML 2020.

BINARY NEURAL NETWORKS’ OPTIMISATION

Nicholas D. Lane, Yarin Gal, Javier Fernández-Marqués, 2019 .

Principled Uncertainty Estimation for High Dimensional Data

José Miguel Hernández-Lobato, Y. Gal, Pascal Notin, 2020 .

Inferring the effectiveness of government interventions against COVID-19

Y. Teh, Y. Gal, J. Salvatier, 2020, Science.

Interlocking Backpropagation: Improving depthwise model-parallelism

Aidan N. Gomez, J. Dean, Y. Gal, 2020, ArXiv.

Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning

Aidan N. Gomez, Y. Gal, D. Marks, 2020, bioRxiv.

Conditional BRUNO : A Deep Recurrent Process for Exchangeable Labelled Data

Y. Gal, A. Gretton, I. Korshunova, 2018 .

Rapid Prototyping of Probabilistic Models : Emerging Challenges in Variational Inference

Y. Gal, 2015 .

The Borel-Kolmogorov paradox

Y. Gal, 2014 .

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions

N. Meinshausen, Y. Gal, Uri Shalit, 2022, ArXiv.

Dirichlet Fragmentation Processes

Zoubin Ghahramani, Y. Gal, Hong Ge, 2015, 1509.04781.

An Empirical study of Binary Neural Networks' Optimisation

Nicholas D. Lane, Yarin Gal, Javier Fernández-Marqués, 2018, ICLR.

Active Testing: Sample-Efficient Model Evaluation

Tom Rainforth, Yarin Gal, Sebastian Farquhar, 2021, ICML.

GeneDisco: A Benchmark for Experimental Design in Drug Discovery pdf

Arash Mehrjou, Yarin Gal, Stefan Bauer, 2021, ICLR.

Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific pdf

Duncan Watson-Parris, Yarin Gal, Philip Stier, 2021, ArXiv.

DARTS without a Validation Set: Optimizing the Marginal Likelihood pdf

Yarin Gal, Clare Lyle, Binxin Ru, 2021, ArXiv.

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

Uri Shalit, Yarin Gal, Andrew Jesson, 2021, ICML.

Sufficient Conditions for Robustness to Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks

Yarin Gal, Lewis Smith, Y. Gal, 2018 .

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

Meng Jin, Atilim Gunecs Baydin, Mark C. M. Cheung, 2020, Astronomy & Astrophysics.

Using Bayesian Optimization to Find Asteroids' Pole Directions

Chedy Raïssi, Yarin Gal, Adam D. Cobb, 2018 .

Inter-domain Deep Gaussian Processes with RKHS Fourier Features

Yarin Gal, Tim G. J. Rudner, Dino Sejdinovic, 2020, International Conference on Machine Learning.

INARA: Intelligent exoplaNet Atmospheric RetrievAl A Machine Learning Retrieval Framework with a Data Set of 3 Million Simulated Exoplanet Atmospheric Spectra

Shawn Domagal-Goldman, Daniel Angerhausen, Giada Arney, 2019 .

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

Mark J. F. Gales, Andrey Malinin, Alexey Noskov, 2021, ArXiv.

Exoplanetary Atmospheric Retrieval via Bayesian Machine Learning

Shawn Domagal-Goldman, Daniel Angerhausen, Giada Arney, 2019 .

Model-based Saliency for the Detection of Adversarial Examples

Yarin Gal, Lisa Schut, Y. Gal, 2019 .

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network pdf

Yee Whye Teh, Yarin Gal, Lewis Smith, 2020, ICML.

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning

Luisa M. Zintgraf, S. Whiteson, Y. Gal, 2019, ICLR.

Learning Invariant Representations for Reinforcement Learning without Reconstruction

S. Levine, Rowan McAllister, R. Calandra, 2020, ICLR.

Mixtures of large-scale dynamic functional brain network modes

Y. Gal, M. Woolrich, S. Adaszewski, 2022, NeuroImage.

epidemics/COVIDNPIs: Inferring the effectiveness of government interventions against COVID-19

Y. Teh, Y. Gal, J. Salvatier, 2020 .

Outcome-Driven Reinforcement Learning via Variational Inference pdf

Sergey Levine, Rowan McAllister, Yarin Gal, 2021, NeurIPS.

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

Michael A. Osborne, Yarin Gal, Sebastian Farquhar, 2019, AISTATS.

Global Geomagnetic Perturbation Forecasting Using Deep Learning

P. Tigas, Y. Gal, R. Mcgranaghan, 2022, Space Weather.

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions

N. Meinshausen, Y. Gal, Uri Shalit, 2022, ArXiv.

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

Y. Gal, Andreas Kirsch, Jannik Kossen, 2022, ArXiv.

Learning Dynamics and Generalization in Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ArXiv.

Mask wearing in community settings reduces SARS-CoV-2 transmission

Y. Gal, R. Zinkov, S. Bhatt, 2022, Proceedings of the National Academy of Sciences of the United States of America.

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

P. Tigas, Y. Gal, B. Scholkopf, 2022, ArXiv.

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

Aidan N. Gomez, Y. Gal, Mrinank Sharma, 2021, ArXiv.

DeDUCE: Generating Counterfactual Explanations At Scale

Y. Gal, J. M. Brauner, L. Schut, 2021 .

Physics informed deep learning to super-resolve and cross-calibrate solar magnetograms

Y. Gal, Michel Deudon, A. G. Baydin, 2021 .

Plex: Towards Reliability using Pretrained Large Model Extensions

Michael W. Dusenberry, Joost R. van Amersfoort, E. Kelly Buchanan, 2022, ArXiv.

Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval

Aidan N. Gomez, Y. Gal, D. Marks, 2022, ICML.

Mixtures of large-scale dynamic functional brain network modes

Y. Gal, M. Woolrich, S. Adaszewski, 2022, NeuroImage.

Bayesian uncertainty quantification for machine-learned models in physics

Y. Gal, P. Koumoutsakos, C. Papadimitriou, 2022, Nature Reviews Physics.

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

Bjoern H Menze, Minh H. Vu, Nisarg A. Shah, 2021, The journal of machine learning for biomedical imaging.

Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

Y. Gal, Andreas Kirsch, 2022, ArXiv.

Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-image Translation

Y. Gal, A. G. Baydin, V. Salvatelli, 2022, The Astrophysical Journal.

Learning from pre-pandemic data to forecast viral antibody escape

Y. Gal, D. Marks, Nathan J. Rollins, 2022, bioRxiv.

Learning Dynamics and Generalization in Deep Reinforcement Learning

Mark Rowland, Will Dabney, Clare Lyle, 2022, ICML.

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions

N. Meinshausen, Y. Gal, Uri Shalit, 2022, NeurIPS.

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

Christos Davatzikos, Gowtham Krishnan Murugesan, Chandan Ganesh, 2021, ArXiv.

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

Y. Gal, Tom Rainforth, Sebastian Farquhar, 2022, NeurIPS.

Changing composition of SARS-CoV-2 lineages and rise of Delta variant in England

Y. Gal, S. Bhatt, G. Nason, 2021, EClinicalMedicine.

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

P. Tigas, Y. Gal, B. Scholkopf, 2022, NeurIPS.

Concrete Problems for Safety in Autonomous Vehicles through Bayesian Deep Learning

Mark van der Wilk, Rowan McAllister, Y. Gal, 2017 .

Exploring Low Rank Training of Deep Neural Networks

Aidan N. Gomez, Jimmy Ba, Y. Gal, 2022, ArXiv.

Publisher Correction: Disease variant prediction with deep generative models of evolutionary data.

Aidan N. Gomez, Y. Gal, D. Marks, 2021, Nature.

Continual Learning via Sequential Function-Space Variational Inference

Tim G. J. Rudner, Y. Teh, Y. Gal, 2023, ICML.

Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

Y. Gal, C. Lintott, N. Eisner, 2022, ArXiv.

Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities

Y. Gal, Andreas Kirsch, 2022, Trans. Mach. Learn. Res..

Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models - a Gentle Tutorial

Mark van der Wilk, Y. Gal, 2014, 1402.1412.

Interlocking Backpropagation: Improving depthwise model-parallelism

Aidan N. Gomez, J. Dean, Y. Gal, 2020, J. Mach. Learn. Res..

CLAM: Selective Clarification for Ambiguous Questions with Large Language Models

Y. Gal, Sebastian Farquhar, Lorenz Kuhn, 2022, arXiv.org.

Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks pdf

Yarin Gal, Lewis Smith, Sebastian Farquhar, 2020, ArXiv.

The effectiveness of eight nonpharmaceutical interventions against COVID-19 in 41 countries

Y. Teh, Y. Gal, J. Salvatier, 2020 .

Understanding the effectiveness of government interventions against the resurgence of COVID-19 in Europe

Y. Gal, L. Finnveden, S. Bhatt, 2021, Nature Communications.

Understanding the effectiveness of government interventions in Europe's second wave of COVID-19

Y. Gal, L. Finnveden, S. Bhatt, 2021, medRxiv.

Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

Roberto Cipolla, Alex Kendall, Yarin Gal, 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Semantics, Modelling, and the Problem of Representation of Meaning - a Brief Survey of Recent Literature pdf

Yarin Gal, Y. Gal, 2014, ArXiv.

2022 Build Counterfactual Estimators Run ExperimentsGenerate Hypotheses Experimental Data Counterfactual Predictions Experimental Design controlintervention covariates

Y. Gal, Stefan Bauer, A. Jesson, 2022 .

Disease variant prediction with deep generative models of evolutionary data

Aidan N. Gomez, Y. Gal, D. Marks, 2021, Nature.

TranceptEVE: Combining Family-specific and Family-agnostic Models of Protein Sequences for Improved Fitness Prediction

Aaron W. Kollasch, Y. Gal, D. Marks, 2022, bioRxiv.

Differentiable Multi-Target Causal Bayesian Experimental Design

Desi R. Ivanova, P. Tigas, Y. Gal, 2023, 2302.10607.

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Y. Gal, Sebastian Farquhar, Lorenz Kuhn, 2023, ArXiv.

CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models

Y. Gal, Sebastian Farquhar, Lorenz Kuhn, 2022, 2212.07769.

Concrete Dropout

Alex Kendall, Yarin Gal, Jiri Hron, 2017, NIPS.

Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam

Didrik Nielsen, Mohammad Emtiyaz Khan, Voot Tangkaratt, 2018, ICML.

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

Michael A. Osborne, Y. Gal, Sebastian Farquhar, 2019, AISTATS.

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

Aidan N. Gomez, Clare Lyle, Y. Gal, 2021, NeurIPS.

Pitfalls in the use of Parallel Inference for the Dirichlet Process

Zoubin Ghahramani, Yarin Gal, Zoubin Ghahramani, 2014, ICML.

Conditional BRUNO: a neural process for exchangeable labelled data

Arthur Gretton, Joni Dambre, Yarin Gal, 2020, ESANN.

Technology readiness levels for machine learning systems

E. Xing, Y. Gal, A. G. Baydin, 2020, Nature Communications.

Domain Invariant Representation Learning with Domain Density Transformations

Y. Gal, A. G. Baydin, A. Nguyen, 2021, NeurIPS.

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

Y. Gal, M. Gales, A. Malinin, 2021, NeurIPS Datasets and Benchmarks.

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?

Sergey Levine, Nicholas Rhinehart, Rowan McAllister, 2020, ICML.

On the Benefits of Invariance in Neural Networks pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.

Invariant Causal Prediction for Block MDPs

Doina Precup, Clare Lyle, Joelle Pineau, 2020, ICML.

VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning

Y. Gal, K. Shiarlis, Maximilian Igl, 2021, J. Mach. Learn. Res..

Identifying Causal Effect Inference Failure with Uncertainty-Aware Models

Y. Gal, Uri Shalit, S. Mindermann, 2020, NeurIPS.

Evaluating Bayesian Deep Learning Methods for Semantic Segmentation pdf

Jishnu Mukhoti, Yarin Gal, Y. Gal, 2018, ArXiv.

Real Time Image Saliency for Black Box Classifiers

Yarin Gal, Piotr Dabkowski, Y. Gal, 2017, NIPS.

Outcome-Driven Reinforcement Learning via Variational Inference

Tim G. J. Rudner, Vitchyr H. Pong, S. Levine, 2021, NeurIPS.

Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning pdf

Yarin Gal, Lucy Fortson, Mike Walmsley, 2019, Monthly Notices of the Royal Astronomical Society.

Towards Robust Evaluations of Continual Learning pdf

Yarin Gal, Sebastian Farquhar, Y. Gal, 2018, ArXiv.

Towards global flood mapping onboard low cost satellites with machine learning

Y. Gal, G. Schumann, A. G. Baydin, 2021, Scientific Reports.

A Note on "Assessing Generalization of SGD via Disagreement"

Y. Gal, Andreas Kirsch, 2022, Trans. Mach. Learn. Res..

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

Joost R. van Amersfoort, P. Tigas, Y. Gal, 2021, NeurIPS.

Deterministic Neural Networks with Inductive Biases Capture Epistemic and Aleatoric Uncertainty

Philip H. S. Torr, Philip H.S. Torr, Jishnu Mukhoti, 2021 .

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

Philip H. S. Torr, Philip H.S. Torr, Jishnu Mukhoti, 2021, ArXiv.

Deep Deterministic Uncertainty: A New Simple Baseline

Philip H. S. Torr, Joost R. van Amersfoort, Y. Gal, 2021, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

On Pitfalls in OoD Detection: Predictive Entropy Considered Harmful

Philip H. S. Torr, Joost R. van Amersfoort, Y. Gal, 2021 .

Learning from pre-pandemic data to forecast viral escape

Y. Gal, D. Marks, Nathan J. Rollins, 2023, bioRxiv.

Deep Deterministic Uncertainty for Semantic Segmentation pdf

Philip H. S. Torr, Philip H.S. Torr, Yarin Gal, 2021, ArXiv.

Learning Sparse Networks Using Targeted Dropout pdf

Geoffrey E. Hinton, Yarin Gal, Kevin Swersky, 2019, ArXiv.

Understanding Measures of Uncertainty for Adversarial Example Detection pdf

Yarin Gal, Lewis Smith, Y. Gal, 2018, UAI.

Flood Detection On Low Cost Orbital Hardware

Y. Gal, G. Schumann, A. G. Baydin, 2019, ArXiv.

BayesOpt Adversarial Attack

Arno Blaas, Yarin Gal, Binxin Ru, 2020, ICLR.

Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control

Luca Cardelli, Matthew Wicker, Luca Laurenti, 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2020, NeurIPS.

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Y. Gal, Sebastian Farquhar, Lorenz Kuhn, 2023, ICLR.

Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers

Tom Rainforth, Yarin Gal, Andreas Kirsch, 2021, 2106.11719.

Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks

Yarin Gal, Lewis Smith, Y. Gal, 2018, 1806.00667.

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

Y. Gal, Tom Rainforth, Sebastian Farquhar, 2021, ICLR.

On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty

Joost R. van Amersfoort, Y. Gal, A. Jesson, 2021, 2102.11409.

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

Michael W. Dusenberry, Tim G. J. Rudner, Angelos Filos, 2021, ArXiv.

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

Bogdan Sacaleanu, Yarin Gal, Luca Costabello, 2021, AISTATS.

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

Stephen Roberts, Yarin Gal, Lewis Smith, 2021, ArXiv.

A Bayesian Perspective on Training Speed and Model Selection pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, NeurIPS.

Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation pdf

Yarin Gal, Gonzalo Mateo-Garcia, Freddie Kalaitzis, 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

A Unifying Bayesian View of Continual Learning pdf

Yarin Gal, Sebastian Farquhar, Y. Gal, 2019, ArXiv.

Using uncertainty-aware machine learning models to study aerosol-cloud interactions

Y. Gal, A. Jesson, A. Douglas, 2022, ArXiv.

An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval pdf

Daniel Angerhausen, Yarin Gal, Adam D. Cobb, 2019, The Astronomical Journal.

On the Importance of Strong Baselines in Bayesian Deep Learning pdf

Jishnu Mukhoti, Yarin Gal, Pontus Stenetorp, 2018, ArXiv.

Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control pdf

Marta Z. Kwiatkowska, Yarin Gal, Rhiannon Michelmore, 2018, ArXiv.

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

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Yarin Gal, 2021, NeurIPS.

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Michael W. Dusenberry, Tim G. J. Rudner, Angelos Filos, 2022, NeurIPS Datasets and Benchmarks.

Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data

Zoubin Ghahramani, Yutian Chen, Yarin Gal, 2015, ICML.

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks pdf

Yarin Gal, Lewis Smith, Milad Alizadeh, 2019, ArXiv.

Viral Evolution and Antibody Escape Mutations using Deep Generative Models

Y. Gal, D. Marks, Nathan J. Rollins, 2021 .

Physics-informed GANs for Coastal Flood Visualization pdf

Chedy Raïssi, Farrukh Chishtie, Christian Requena-Mesa, 2020, ArXiv.

BatchGFN: Generative Flow Networks for Batch Active Learning

Y. Gal, Y. Bengio, T. Deleu, 2023, ArXiv.

Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning

Y. Gal, Andreas Kirsch, A. Jesson, 2021, 2106.12059.

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients

Joost R. van Amersfoort, Shyam A. Tailor, Y. Gal, 2022, ICLR.

Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization

Natalia Díaz Rodríguez, Y. Gal, Alexander Lavin, 2021, ArXiv.

KL Guided Domain Adaptation

Philip H. S. Torr, Y. Gal, A. Nguyen, 2021, ICLR.

Uncertainty quantification for virtual diagnostic of particle accelerators

Yarin Gal, Lewis Smith, Adi Hanuka, 2021, Physical Review Accelerators and Beams.

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

Y. Gal, V. Salvatelli, M. Janvier, 2020, Astronomy & Astrophysics.

Auto-Calibration of Remote Sensing Solar Telescopes with Deep Learning pdf

Meng Jin, Yarin Gal, Mark Cheung, 2019, ArXiv.

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

Nicolas Papernot, Y. Gal, V. Papyan, 2023, ArXiv.

The Curse of Recursion: Training on Generated Data Makes Models Forget

Nicolas Papernot, Y. Gal, Ilia Shumailov, 2023, ArXiv.

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers pdf

Yarin Gal, Aidan N. Gomez, Tim Z. Xiao, 2020, ArXiv.

In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning

Y. Gal, Tom Rainforth, Jannik Kossen, 2023, ArXiv.

Radial Bayesian Neural Networks: Robust Variational Inference In Big Models pdf

Yarin Gal, Sebastian Farquhar, Michael Osborne, 2019, ArXiv.

Differentially Private Continual Learning pdf

Yarin Gal, Sebastian Farquhar, Y. Gal, 2019, ArXiv.

M ODEL D EMENTIA : G ENERATED D ATA M AKES M ODELS F ORGET

Nicolas Papernot, Y. Gal, Ilia Shumailov, 2023 .

Prediction-Oriented Bayesian Active Learning

Freddie Bickford Smith, Y. Gal, Tom Rainforth, 2023, AISTATS.

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

Y. Gal, Sebastian Farquhar, Lewis Smith, 2020, NeurIPS.

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Tim G. J. Rudner, Y. Teh, Y. Gal, 2022, NeurIPS.

Robustness to Pruning Predicts Generalization in Deep Neural Networks pdf

Yarin Gal, Clare Lyle, Aidan N. Gomez, 2021, ArXiv.

Adversarial recovery of agent rewards from latent spaces of the limit order book pdf

Yuanbo Wang, Ricardo Silva, Yarin Gal, 2019, ArXiv.

Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs

Richard E. Turner, Richard Turner, Yarin Gal, 2015, ICML.

Learning from pre-pandemic data to forecast viral antibody escape Authors

Y. Gal, D. Marks, Nathan J. Rollins, 2022 .

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression pdf

Yarin Gal, Lewis Smith, Joost van Amersfoort, 2021, ArXiv.

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

Chris Xiaoxuan Lu, Angelos Filos, Y. Gal, 2023, ArXiv.

Model and Data Uncertainty for Satellite Time Series Forecasting with Deep Recurrent Models

Marc Rußwurm, Xiao Xiang Zhu, Yarin Gal, 2020, IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium.

Revisiting Automated Prompting: Are We Actually Doing Better?

Y. Gal, R. Mullins, Ilia Shumailov, 2023, ACL.

Differentiable Multi-Target Causal Bayesian Experimental Design

Desi R. Ivanova, P. Tigas, Y. Gal, 2023, ICML.

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

Yarin Gal, Andreas Kirsch, Y. Gal, 2021, ArXiv.

A Generative Deep Recurrent Model for Exchangeable Data

Arthur Gretton, Jonas Degrave, Joni Dambre, 2018 .

A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions pdf

Yarin Gal, Andreas Kirsch, Sebastian Farquhar, 2021, ArXiv.

Single Shot Structured Pruning Before Training pdf

Nicholas Lane, Yarin Gal, Milad Alizadeh, 2020, ArXiv.

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

S. Levine, Clare Lyle, Angelos Filos, 2021, ICML.

Fine-tuning can cripple your foundation model; preserving features may be the solution

Philip H. S. Torr, Y. Gal, P. Dokania, 2023, ArXiv.

Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning pdf

Yarin Gal, Andreas Kirsch, Clare Lyle, 2020, ArXiv.

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Aidan N. Gomez, Y. Gal, Mrinank Sharma, 2022, ICML.

In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning

Y. Gal, Tom Rainforth, Jannik Kossen, 2023, ArXiv.

DiscoBAX: Discovery of optimal intervention sets in genomic experiment design

Clare Lyle, Y. Gal, Stefan Bauer, 2023, ICML.

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

Zoubin Ghahramani, Y. Gal, 2015, ArXiv.

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

Chris Xiaoxuan Lu, Angelos Filos, Y. Gal, 2023, ArXiv.

Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning

Y. Gal, Andreas Kirsch, A. Jesson, 2021, 2106.12059.

Machine Learning for Generalizable Prediction of Flood Susceptibility pdf

Yarin Gal, Piotr Bilinski, Dylan J. Fitzpatrick, 2019, ArXiv.

Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning

Y. Gal, A. G. Baydin, V. Salvatelli, 2021 .

How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Y. Gal, Owain Evans, S. Mindermann, 2023, ArXiv.

Uncertainty Estimation Using a Single Deep Deterministic Neural Network

Joost R. van Amersfoort, Y. Gal, Lewis Smith, 2020, ICML.

In-Context Learning Learns Label Relationships but Is Not Conventional Learning

Y. Gal, Tom Rainforth, Jannik Kossen, 2023, 2307.12375.

Learning Invariant Representations for Reinforcement Learning without Reconstruction pdf

Rowan McAllister, Yarin Gal, Roberto Calandra, 2020, ICLR.

Generalizing from a few environments in safety-critical reinforcement learning pdf

Yarin Gal, Angelos Filos, Owain Evans, 2019, ArXiv.

Appendix of Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2021 .

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.