


default search action
Yarin Gal
Person information
- affiliation: University of Oxford, Department of Computer Science, UK
- affiliation: Alan Turing Institute, London, UK
Refine list

refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j12]Sebastian Farquhar
, Jannik Kossen, Lorenz Kuhn, Yarin Gal
:
Detecting hallucinations in large language models using semantic entropy. Nat. 630(8017): 625-630 (2024) - [j11]Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao
, Nicolas Papernot, Ross J. Anderson
, Yarin Gal
:
AI models collapse when trained on recursively generated data. Nat. 631(8022): 755-759 (2024) - [j10]Björn Lütjens, Brandon Leshchinskiy, Océane Boulais, Farrukh Chishtie
, Natalia Díaz Rodríguez, Margaux Masson-Forsythe, Ana Mata-Payerro
, Christian Requena-Mesa, Aruna Sankaranarayanan, Aaron Piña, Yarin Gal
, Chedy Raïssi, Alexander Lavin
, Dava Newman
:
Generating Physically-Consistent Satellite Imagery for Climate Visualizations. IEEE Trans. Geosci. Remote. Sens. 62: 1-11 (2024) - [j9]Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. Trans. Mach. Learn. Res. 2024 (2024) - [c80]Jannik Kossen, Yarin Gal, Tom Rainforth:
In-Context Learning Learns Label Relationships but Is Not Conventional Learning. ICLR 2024 - [c79]Lorenzo Pacchiardi, Alex James Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Markus Brauner:
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions. ICLR 2024 - [c78]David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan:
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches. ICML 2024 - [c77]Andrew Jesson, Chris Lu, Gunshi Gupta, Nicolas Beltran-Velez, Angelos Filos, Jakob Nicolaus Foerster, Yarin Gal:
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages. ICML 2024 - [c76]Amir Mohammad Karimi-Mamaghan, Panagiotis Tigas, Karl Henrik Johansson, Yarin Gal, Yashas Annadani, Stefan Bauer:
Challenges and Considerations in the Evaluation of Bayesian Causal Discovery. ICML 2024 - [c75]Angus Nicolson, Yarin Gal, J. Alison Noble:
TextCAVs: Debugging Vision Models Using Text. ISIC/iMIMIC/EARTH/DeCaF@MICCAI 2024: 99-109 - [c74]Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David M. Blei:
Estimating the Hallucination Rate of Generative AI. NeurIPS 2024 - [c73]Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen:
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities. NeurIPS 2024 - [i146]Kunal Handa, Yarin Gal, Ellie Pavlick, Noah D. Goodman, Jacob Andreas, Alex Tamkin, Belinda Z. Li:
Bayesian Preference Elicitation with Language Models. CoRR abs/2403.05534 (2024) - [i145]Angus Nicolson, Lisa Schut, J. Alison Noble, Yarin Gal:
Explaining Explainability: Understanding Concept Activation Vectors. CoRR abs/2404.03713 (2024) - [i144]Gunshi Gupta, Karmesh Yadav, Yarin Gal, Dhruv Batra, Zsolt Kira, Cong Lu, Tim G. J. Rudner:
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control. CoRR abs/2405.05852 (2024) - [i143]Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen:
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities. CoRR abs/2405.20003 (2024) - [i142]Amir Mohammad Karimi-Mamaghan, Panagiotis Tigas, Karl Henrik Johansson, Yarin Gal, Yashas Annadani, Stefan Bauer:
Challenges and Considerations in the Evaluation of Bayesian Causal Discovery. CoRR abs/2406.03209 (2024) - [i141]Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David M. Blei:
Estimating the Hallucination Rate of Generative AI. CoRR abs/2406.07457 (2024) - [i140]Luckeciano C. Melo, Panagiotis Tigas, Alessandro Abate, Yarin Gal:
Deep Bayesian Active Learning for Preference Modeling in Large Language Models. CoRR abs/2406.10023 (2024) - [i139]Muhammed Razzak, Andreas Kirsch, Yarin Gal:
The Benefits and Risks of Transductive Approaches for AI Fairness. CoRR abs/2406.12011 (2024) - [i138]Jannik Kossen, Jiatong Han, Muhammed Razzak, Lisa Schut, Shreshth A. Malik, Yarin Gal:
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs. CoRR abs/2406.15927 (2024) - [i137]Yoav Gelberg, Tycho F. A. van der Ouderaa, Mark van der Wilk, Yarin Gal:
Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks. CoRR abs/2408.05496 (2024) - [i136]Angus Nicolson, Yarin Gal, J. Alison Noble:
TextCAVs: Debugging vision models using text. CoRR abs/2408.08652 (2024) - [i135]Luckeciano C. Melo, Alessandro Abate, Yarin Gal:
Temporal-Difference Variational Continual Learning. CoRR abs/2410.07812 (2024) - [i134]Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, Eric Winsor, Jerome Wynne, Yarin Gal, Xander Davies:
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents. CoRR abs/2410.09024 (2024) - [i133]Benedict Aaron Tjandra, Muhammed Razzak, Jannik Kossen, Kunal Handa, Yarin Gal:
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy. CoRR abs/2410.17234 (2024) - [i132]Hazel Kim, Adel Bibi, Philip Torr, Yarin Gal:
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Unanswerable Questions and Ambiguous Prompts. CoRR abs/2412.10246 (2024) - 2023
- [j8]Andreas Kirsch, Sebastian Farquhar, Parmida Atighehchian, Andrew Jesson, Frédéric Branchaud-Charron, Yarin Gal:
Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning. Trans. Mach. Learn. Res. 2023 (2023) - [c72]Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert D. Mullins, Yarin Gal:
Revisiting Automated Prompting: Are We Actually Doing Better? ACL (2) 2023: 1822-1832 - [c71]Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth:
Prediction-Oriented Bayesian Active Learning. AISTATS 2023: 7331-7348 - [c70]Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal:
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? CLeaR 2023: 386-407 - [c69]Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal:
Deep Deterministic Uncertainty: A New Simple Baseline. CVPR 2023: 24384-24394 - [c68]Lorenz Kuhn, Yarin Gal, Sebastian Farquhar:
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. ICLR 2023 - [c67]Clare Lyle, Arash Mehrjou, Pascal Notin, Andrew Jesson, Stefan Bauer, Yarin Gal, Patrick Schwab:
DiscoBAX: Discovery of optimal intervention sets in genomic experiment design. ICML 2023: 23170-23189 - [c66]Panagiotis Tigas, Yashas Annadani, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster, Stefan Bauer:
Differentiable Multi-Target Causal Bayesian Experimental Design. ICML 2023: 34263-34279 - [c65]Kelsey Doerksen, Yarin Gal, Freddie Kalaitzis, Cristian Rossi, David Petit, Sihan Li, Simon J. Dadson:
Precipitation-Triggered Landslide Prediction in Nepal Using Machine Learning and Deep Learning. IGARSS 2023: 4962-4965 - [c64]Pascal Notin, Aaron Kollasch, Daniel Ritter, Lood van Niekerk, Steffanie Paul, Han Spinner, Nathan J. Rollins, Ada Shaw, Rose Orenbuch, Ruben Weitzman, Jonathan Frazer, Mafalda Dias, Dinko Franceschi, Yarin Gal, Debora S. Marks:
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design. NeurIPS 2023 - [c63]Pascal Notin, Ruben Weitzman, Debora S. Marks, Yarin Gal:
ProteinNPT: Improving protein property prediction and design with non-parametric transformers. NeurIPS 2023 - [i131]Maëlys Solal, Andrew Jesson, Yarin Gal, Alyson Douglas:
Using uncertainty-aware machine learning models to study aerosol-cloud interactions. CoRR abs/2301.11921 (2023) - [i130]Lorenz Kuhn, Yarin Gal, Sebastian Farquhar:
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. CoRR abs/2302.09664 (2023) - [i129]Yashas Annadani, Panagiotis Tigas, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster, Stefan Bauer:
Differentiable Multi-Target Causal Bayesian Experimental Design. CoRR abs/2302.10607 (2023) - [i128]Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert D. Mullins, Yarin Gal:
Revisiting Automated Prompting: Are We Actually Doing Better? CoRR abs/2304.03609 (2023) - [i127]Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth:
Prediction-Oriented Bayesian Active Learning. CoRR abs/2304.08151 (2023) - [i126]Ilia Shumailov, Zakhar Shumaylov
, Yiren Zhao, Yarin Gal, Nicolas Papernot, Ross J. Anderson:
The Curse of Recursion: Training on Generated Data Makes Models Forget. CoRR abs/2305.17493 (2023) - [i125]Andrew Jesson, Chris Lu, Gunshi Gupta, Angelos Filos, Jakob Nicolaus Foerster, Yarin Gal:
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages. CoRR abs/2306.01460 (2023) - [i124]Shreshth A. Malik, Salem Lahlou, Andrew Jesson, Moksh Jain, Nikolay Malkin, Tristan Deleu, Yoshua Bengio, Yarin Gal:
BatchGFN: Generative Flow Networks for Batch Active Learning. CoRR abs/2306.15058 (2023) - [i123]David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan:
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem? CoRR abs/2307.10719 (2023) - [i122]Jannik Kossen, Tom Rainforth, Yarin Gal:
In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning. CoRR abs/2307.12375 (2023) - [i121]Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. CoRR abs/2308.13320 (2023) - [i120]Lorenzo Pacchiardi, Alex J. Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Brauner:
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions. CoRR abs/2309.15840 (2023) - [i119]Peter A. Zachares, Vahan Hovhannisyan, Alan Mosca, Yarin Gal:
Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements. CoRR abs/2311.00444 (2023) - [i118]Clare Lyle, Arash Mehrjou, Pascal Notin, Andrew Jesson, Stefan Bauer, Yarin Gal, Patrick Schwab:
DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design. CoRR abs/2312.04064 (2023) - [i117]Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal:
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? CoRR abs/2312.17168 (2023) - [i116]Tim G. J. Rudner, Zonghao Chen, Yee Whye Teh, Yarin Gal:
Tractable Function-Space Variational Inference in Bayesian Neural Networks. CoRR abs/2312.17199 (2023) - [i115]Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal:
Continual Learning via Sequential Function-Space Variational Inference. CoRR abs/2312.17210 (2023) - 2022
- [j7]Aidan N. Gomez, Oscar Key, Kuba Perlin, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal:
Interlocking Backpropagation: Improving depthwise model-parallelism. J. Mach. Learn. Res. 23: 171:1-171:28 (2022) - [j6]Chetan Gohil, Evan Roberts, Ryan C. Timms, Alex Skates, Cameron Higgins
, Andrew Quinn
, Usama Pervaiz, Joost van Amersfoort, Pascal Notin
, Yarin Gal, Stanislaw Adaszewski, Mark W. Woolrich:
Mixtures of large-scale dynamic functional brain network modes. NeuroImage 263: 119595 (2022) - [j5]Raghav Mehta
, Thomas Christinck
, Tanya Nair, Aurélie Bussy
, Swapna Premasiri, Manuela Costantino
, M. Mallar Chakravarthy, Douglas L. Arnold
, Yarin Gal
, Tal Arbel:
Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference. IEEE Trans. Medical Imaging 41(2): 360-373 (2022) - [j4]Andreas Kirsch, Yarin Gal:
A Note on "Assessing Generalization of SGD via Disagreement". Trans. Mach. Learn. Res. 2022 (2022) - [j3]Andreas Kirsch, Yarin Gal:
Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities. Trans. Mach. Learn. Res. 2022 (2022) - [c62]Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal:
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. ICLR 2022 - [c61]Arash Mehrjou, Ashkan Soleymani, Andrew Jesson, Pascal Notin, Yarin Gal, Stefan Bauer, Patrick Schwab:
GeneDisco: A Benchmark for Experimental Design in Drug Discovery. ICLR 2022 - [c60]A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip H. S. Torr, Atilim Gunes Baydin:
KL Guided Domain Adaptation. ICLR 2022 - [c59]Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal:
Learning Dynamics and Generalization in Deep Reinforcement Learning. ICML 2022: 14560-14581 - [c58]Sören Mindermann, Jan Markus Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal:
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt. ICML 2022: 15630-15649 - [c57]Pascal Notin
, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado
, Aidan N. Gomez, Debora S. Marks, Yarin Gal:
Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval. ICML 2022: 16990-17017 - [c56]Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal:
Continual Learning via Sequential Function-Space Variational Inference. ICML 2022: 18871-18887 - [c55]Andrew Jesson, Alyson Douglas, Peter Manshausen, Maëlys Solal, Nicolai Meinshausen, Philip Stier, Yarin Gal, Uri Shalit:
Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions. NeurIPS 2022 - [c54]Jannik Kossen, Sebastian Farquhar, Yarin Gal, Thomas Rainforth:
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation. NeurIPS 2022 - [c53]Tim G. J. Rudner, Zonghao Chen, Yee Whye Teh, Yarin Gal:
Tractable Function-Space Variational Inference in Bayesian Neural Networks. NeurIPS 2022 - [c52]Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer:
Interventions, Where and How? Experimental Design for Causal Models at Scale. NeurIPS 2022 - [i114]Andreas Kirsch, Yarin Gal:
A Note on "Assessing Generalization of SGD via Disagreement". CoRR abs/2202.01851 (2022) - [i113]Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth:
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation. CoRR abs/2202.06881 (2022) - [i112]Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal:
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. CoRR abs/2202.08132 (2022) - [i111]Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer:
Interventions, Where and How? Experimental Design for Causal Models at Scale. CoRR abs/2203.02016 (2022) - [i110]Andrew Jesson, Alyson Douglas, Peter Manshausen, Nicolai Meinshausen, Philip Stier, Yarin Gal, Uri Shalit:
Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions. CoRR abs/2204.10022 (2022) - [i109]Andreas Kirsch, Jannik Kossen, Yarin Gal:
Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling. CoRR abs/2205.08766 (2022) - [i108]Vishal Upendran, Panagiotis Tigas, Banafsheh Ferdousi, Téo Bloch, Mark C. M. Cheung, Siddha Ganju, Asti Bhatt, Ryan M. McGranaghan, Yarin Gal:
Global geomagnetic perturbation forecasting using Deep Learning. CoRR abs/2205.12734 (2022) - [i107]Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado
, Aidan N. Gomez, Debora S. Marks, Yarin Gal:
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval. CoRR abs/2205.13760 (2022) - [i106]Clare Lyle, Mark Rowland, Will Dabney, Marta Kwiatkowska, Yarin Gal:
Learning Dynamics and Generalization in Reinforcement Learning. CoRR abs/2206.02126 (2022) - [i105]Sören Mindermann, Jan Markus Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal:
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt. CoRR abs/2206.07137 (2022) - [i104]Dustin Tran, Jeremiah Z. Liu, Michael W. Dusenberry, Du Phan, Mark Collier, Jie Ren, Kehang Han, Zi Wang, Zelda Mariet, Huiyi Hu, Neil Band, Tim G. J. Rudner, Karan Singhal, Zachary Nado, Joost van Amersfoort, Andreas Kirsch, Rodolphe Jenatton, Nithum Thain, Honglin Yuan, Kelly Buchanan, Kevin Murphy, D. Sculley, Yarin Gal, Zoubin Ghahramani, Jasper Snoek, Balaji Lakshminarayanan:
Plex: Towards Reliability using Pretrained Large Model Extensions. CoRR abs/2207.07411 (2022) - [i103]Andreas Kirsch, Yarin Gal:
Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities. CoRR abs/2208.00549 (2022) - [i102]Valentina Salvatelli, Luiz F. G. dos Santos, Souvik Bose, Brad Neuberg, Mark C. M. Cheung, Miho Janvier, Meng Jin, Yarin Gal, Atilim Gunes Baydin:
Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation. CoRR abs/2208.09512 (2022) - [i101]Siddhartha Rao Kamalakara, Acyr Locatelli, Bharat Venkitesh, Jimmy Ba, Yarin Gal, Aidan N. Gomez:
Exploring Low Rank Training of Deep Neural Networks. CoRR abs/2209.13569 (2022) - [i100]Shreshth A. Malik, Nora L. Eisner, Chris J. Lintott, Yarin Gal:
Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels. CoRR abs/2211.06903 (2022) - [i99]Neil Band, Tim G. J. Rudner, Qixuan Feng, Angelos Filos, Zachary Nado, Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal:
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks. CoRR abs/2211.12717 (2022) - [i98]Lorenz Kuhn, Yarin Gal, Sebastian Farquhar:
CLAM: Selective Clarification for Ambiguous Questions with Large Language Models. CoRR abs/2212.07769 (2022) - [i97]Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh:
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations. CoRR abs/2212.13936 (2022) - 2021
- [j2]Luisa M. Zintgraf, Sebastian Schulze, Cong Lu, Leo Feng, Maximilian Igl, Kyriacos Shiarlis, Yarin Gal, Katja Hofmann, Shimon Whiteson:
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning. J. Mach. Learn. Res. 22: 289:1-289:39 (2021) - [c51]Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal:
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties. AISTATS 2021: 1756-1764 - [c50]Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, Sergey Levine:
Learning Invariant Representations for Reinforcement Learning without Reconstruction. ICLR 2021 - [c49]Sebastian Farquhar, Yarin Gal, Tom Rainforth:
On Statistical Bias In Active Learning: How and When to Fix It. ICLR 2021 - [c48]Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar:
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning. ICML 2021: 3305-3317 - [c47]Andrew Jesson, Sören Mindermann, Yarin Gal, Uri Shalit:
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding. ICML 2021: 4829-4838 - [c46]Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth:
Active Testing: Sample-Efficient Model Evaluation. ICML 2021: 5753-5763 - [c45]Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth:
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes. ICML 2021: 9148-9156 - [c44]Neil Band, Tim G. J. Rudner, Qixuan Feng, Angelos Filos, Zachary Nado, Mike Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal:
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks. NeurIPS Datasets and Benchmarks 2021 - [c43]Andrew Jesson, Panagiotis Tigas, Joost van Amersfoort, Andreas Kirsch, Uri Shalit, Yarin Gal:
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data. NeurIPS 2021: 30465-30478 - [c42]Andrey Malinin, Neil Band, Yarin Gal, Mark J. F. Gales, Alexander Ganshin, German Chesnokov, Alexey Noskov, Andrey Ploskonosov, Liudmila Prokhorenkova, Ivan Provilkov, Vatsal Raina, Vyas Raina, Denis Roginskiy, Mariya Shmatova, Panagiotis Tigas, Boris Yangel:
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks. NeurIPS Datasets and Benchmarks 2021 - [c41]Andrew Gordon Wilson, Pavel Izmailov, Matthew D. Hoffman, Yarin Gal, Yingzhen Li, Melanie F. Pradier, Sharad Vikram, Andrew Y. K. Foong, Sanae Lotfi, Sebastian Farquhar:
Evaluating Approximate Inference in Bayesian Deep Learning. NeurIPS (Competition and Demos) 2021: 113-124 - [c40]Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal:
Improving black-box optimization in VAE latent space using decoder uncertainty. NeurIPS 2021: 802-814 - [c39]Robin Ru, Clare Lyle, Lisa Schut, Miroslav Fil, Mark van der Wilk, Yarin Gal:
Speedy Performance Estimation for Neural Architecture Search. NeurIPS 2021: 4079-4092 - [c38]A. Tuan Nguyen, Toan Tran, Yarin Gal, Atilim Gunes Baydin:
Domain Invariant Representation Learning with Domain Density Transformations. NeurIPS 2021: 5264-5275 - [c37]Tim G. J. Rudner, Vitchyr Pong, Rowan McAllister, Yarin Gal, Sergey Levine:
Outcome-Driven Reinforcement Learning via Variational Inference. NeurIPS 2021: 13045-13058 - [c36]Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh:
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations. NeurIPS 2021: 28376-28389 - [c35]Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Thomas Rainforth, Yarin Gal:
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning. NeurIPS 2021: 28742-28756 - [i96]Alexander Lavin, Ciarán M. Gilligan-Lee, Alessya Visnjic, Siddha Ganju, Dava Newman, Sujoy Ganguly, Danny Lange, Atilim Günes Baydin, Amit Sharma, Adam Gibson, Yarin Gal, Eric P. Xing, Chris Mattmann, James Parr:
Technology Readiness Levels for Machine Learning Systems. CoRR abs/2101.03989 (2021) - [i95]Sebastian Farquhar, Yarin Gal, Tom Rainforth:
On Statistical Bias In Active Learning: How and When To Fix It. CoRR abs/2101.11665 (2021) - [i94]Panagiotis Tigas, Téo Bloch
, Vishal Upendran, Banafsheh Ferdoushi, Mark C. M. Cheung, Siddha Ganju, Ryan M. McGranaghan
, Yarin Gal, Asti Bhatt:
Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition. CoRR abs/2102.01447 (2021) - [i93]A. Tuan Nguyen, Toan Tran, Yarin Gal, Atilim Günes Baydin:
Domain Invariant Representation Learning with Domain Density Transformations. CoRR abs/2102.05082 (2021) - [i92]Joost