Tim G. J. Rudner

Incoming Assistant Professor & Faculty Fellow, New York University

PhD Candidate, Department of Computer Science, University of Oxford

Oxford Applied & Theoretical Machine Learning Group (OATML)

Oxford Computational Statistics & Machine Learning Group (OxCSML)

tim.rudner [AT] cs.ox.ac.uk

About

I am a PhD Candidate in the Department of Computer Science at the University of Oxford, where I conduct research on probabilistic machine learning with Yarin Gal and Yee Whye Teh. The goal of my research is to develop methods and theoretical insights that enable the safe deployment of machine learning systems in safety-critical settings by drawing on tools from variational Bayesian inference and reinforcement learning. I am particularly interested in Bayesian uncertainty quantification in deep learning, probabilistic inference in reinforcement learning and control, and AI safety. For my work on safe decision-making under uncertainty, I received the 2021 Qualcomm Innovation Fellowship. I care deeply about equitable access to education and serve as an Equality, Diversity & Inclusion Fellow at the University of Oxford.

I am also an AI Fellow at Georgetown University's Center for Security and Emerging Technology and a Rhodes Scholar.

Bio

I obtained an undergraduate degree in mathematics and economics from Yale University, where I received the Charles E. Clark Memorial Award for Academic Excellence. Subsequently, I earned a master's degree in statistics from the University of Oxford, where I was advised by Dino Sejdinovic. During my PhD, I was fortunate to work with Sergey Levine at the University of California, Berkeley and with Sekhar Tatikonda at Yale University. Prior to coming to Oxford, I conducted research on game theoretic equilibria in digital goods markets, systemic risk in financial markets, and drivers of financial crises. I am a member of the Oxford Center for Doctoral Training in Autonomous Intelligent Machines & Systems (AIMS) and the OECD Network of Experts, as well as a Fellow of the German Academic Scholarship Foundation.

News

Recent
All

[14/09/22] New publication: Tractable Function-Space Variational Inference in Bayesian Neural Networks.
[17/07/22] In the fall, I will join NYU as an Assistant Professor and Faculty Fellow at the Center for Data Science.
[17/07/22] New publication: Continual Learning via Sequential Function-Space Variational Inference. [View code]
[14/07/22] New paper: Plex: Towards Reliability Using Pretrained Large Model Extensions with Google AI. [Read blog]
[28/06/22] Outstanding Paper Award for Challenges and Opportunities in Offline RL from Visual Observations at L-DOD.
[09/06/22] Code release: We released V-D4RL, a benchmark to assess robustness in offline RL from images [View paper].
[01/12/21] CSET paper series: Key Concepts in AI Safety: Specification in Machine Learning.
[11/10/21] I was selected to serve as an Equality, Diversity & Inclusion Fellow at the University of Oxford.
[10/10/21] New publication: Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks. [Code]
[28/09/21] New publication: Outcome-Driven Reinforcement Learning via Variational Inference. [View animations]
[28/09/21] New publication: On Pathologies in KL-Regularized RL from Expert Demonstrations. [View animations]
[06/08/21] I was awarded the Qualcomm Innovation Fellowship for my work on safe decision-making under uncertainty.
[07/06/21] Code release: We released Uncertainty Baselines for Bayesian Deep Learning. [View paper]
[03/06/21] I received a UAI 2021 Outstanding Reviewer Award (top 5% of reviewers).
[08/04/21] New publication: On Signal-to-Noise Ratio Issues in VI for Deep GPs was accepted to ICML 2021. [View code]

[14/09/22] New publication: Tractable Function-Space Variational Inference in Bayesian Neural Networks.
[17/07/22] In the fall, I will join NYU as an Assistant Professor and Faculty Fellow at the Center for Data Science.
[17/07/22] New publication: Continual Learning via Sequential Function-Space Variational Inference. [View code]
[14/07/22] New paper: Plex: Towards Reliability Using Pretrained Large Model Extensions with Google AI. [Read blog]
[28/06/22] Outstanding Paper Award for Challenges and Opportunities in Offline RL from Visual Observations at L-DOD.
[09/06/22] Code release: We released V-D4RL, a benchmark to assess robustness in offline RL from images [View paper].
[01/12/21] CSET paper series: Key Concepts in AI Safety: Specification in Machine Learning.
[11/10/21] I was selected to serve as an Equality, Diversity & Inclusion Fellow at the University of Oxford.
[10/10/21] New publication: Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks. [Code]
[28/09/21] New publication: Outcome-Driven Reinforcement Learning via Variational Inference. [View animations]
[28/09/21] New publication: On Pathologies in KL-Regularized RL from Expert Demonstrations. [View animations]
[06/08/21] I was awarded the Qualcomm Innovation Fellowship for my work on safe decision-making under uncertainty.
[07/06/21] Code release: We released Uncertainty Baselines for Bayesian Deep Learning. [View paper]
[03/06/21] I received a UAI 2021 Outstanding Reviewer Award (top 5% of reviewers).
[08/04/21] New publication: On Signal-to-Noise Ratio Issues in VI for Deep GPs was accepted to ICML 2021. [View code]
[21/04/21] I gave a talk on AI safety at the Joint Artificial Intelligence Center's Subcommittee on Responsible AI.
[17/03/21] CSET paper series: Key Concepts in AI Safety: An Overview, Robustness, Interpretability.
[17/12/20] I gave an invited talk on Outcome-Driven Reinforcement Learning via Variational Inference at UCLA & MPI.
[16/12/20] I gave an invited guest lecture on Bayesian Deep Learning at University College London.
[16/12/20] I gave an invited talk on “A Non-Technical Guide to Modern Machine Learning” at Georgetown University.
[24/11/20] I organized the 1st Oxford-Google Workshop on Reliable Machine Learning.
[21/10/20] I received a NeurIPS 2020 Outstanding Reviewer Award (top 10% of reviewers).
[16/10/20] I gave an invited talk on Inter-domain Deep Gaussian Processes at the University of Cambridge.
[15/09/20] I received an ICML 2020 Outstanding Reviewer Award (top 33% of reviewers).
[13/08/20] I gave an invited talk on Inter-domain Deep Gaussian Processes at the UCL Center for Artificial Intelligence.
[12/07/20] New publication: Inter-domain Deep Gaussian Processes was accepted to ICML 2020.
[01/04/20] I joined the OECD's Working Groups on Trustworthy AI and AI Classification as an invited expert.
[18/12/19] I gave a talk on Inter-domain Deep Gaussian Processes at the Turing Institute Workshop on Deep Structures.
[03/09/19] New publication: Our paper on variational inference in RL was accepted for a Spotlight Talk at NeurIPS 2019.
[03/09/19] I received a NeurIPS 2019 Outstanding Reviewer Award (top 10% of reviewers).
[01/07/19] I joined Georgetown University's Center for Security and Emerging Technology (CSET) as an AI Fellow.
[15/06/19] Code release: We released the first in a series of Bayesian Deep Learning benchmark tasks.
[02/06/19] I received an ICML 2019 Outstanding Reviewer Award (top 5% of reviewers).
[05-08/19] I interned at Amazon Research, where I worked with Zhenwen Dai, Andreas Damianou, and Neil Lawrence.
[12/02/19] Code release: We launched the StarCraft Multi-Agent Challenge along with a Python library for multi-agent RL.
[05/12/18] New publication: My work on ML-aided disaster response was accepted into AAAI 2019 and is now on arXiv.
[08/10/18] I joined the Oxford Applied & Theoretical Machine Learning Group (OATML) to work with Yarin Gal.
[08-09/18] I worked on probabilistic multi-agent reinforcement learning at Fractal Industries in Washington, D.C.
[06-08/18] I worked at the Frontier Development Lab to develop machine learning methods for disaster response.
[18/02/18] I attended the World Government Summit 2018 in Dubai as a delegate of the Rhodes Trust.
[09/10/17] I started my PhD at the University of Oxford as a member of the AIMS Center for Doctoral Training.

Publications

Most recent publications on Google Scholar.

Selected
All

Probabilistic Machine Learning

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Tim G. J. Rudner*, Zonghao Chen*, Yee Whye Teh, Yarin Gal

NeurIPS '22 Conference on Neural Information Processing Systems. 2022.

Paper Poster Bibtex

@inproceedings{
    Rudner2022fsvi,
    title={{T}ractabe {F}unction-{S}pace {V}ariational {I}nference in {B}ayesian {N}eural {N}etworks},
    author={Tim G. J. Rudner and Zonghao Chen and Yee Whye Teh and Yarin Gal},
    journal = {Advances in Neural Information Processing Systems 35},
    year = {2022},
}

Continual Learning via Sequential Function-Space Variational Inference

Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal

ICML '22 International Conference on Machine Learning. 2022.

Paper Code Talk Slides Bibtex

@InProceedings{Rudner2021sfsvi,
    author={Tim G. J. Rudner and Freddie Bickford Smith and Qixuan Feng and Yee Whye Teh and Yarin Gal},
    title={{C}ontinual {L}earning via {S}equential {F}unction-{S}pace {V}ariational {I}nference},
    booktitle = {Proceedings of the 38th International Conference on Machine Learning},
    year = {2022},
    series = {Proceedings of Machine Learning Research},
    publisher = {PMLR},
}

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

Tim G. J. Rudner*, Oscar Key*, Yarin Gal, Tom Rainforth

ICML '21 International Conference on Machine Learning. 2021.

arXiv Code Talk Slides Poster Bibtex

@InProceedings{rudner2021SNRIssuesInDGPs,
    author = {Tim G. J. Rudner and Oscar Key and Yarin Gal and Tom Rainforth},
    title = {{O}n {S}ignal-to-{N}oise {R}atio {I}ssues in {V}ariational {I}nference for {D}eep {G}aussian {P}rocesses},
    booktitle = {Proceedings of the 38th International Conference on Machine Learning},
    year = {2021},
    series = {Proceedings of Machine Learning Research},
    address = {Online},
    publisher = {PMLR},
}

Inter-domain Deep Gaussian Processes

Tim G. J. Rudner, Dino Sejdinovic, Yarin Gal

ICML '20 International Conference on Machine Learning. 2020.

arXiv Website Talk Slides Bibtex

@InProceedings{rudner2020InterDomainDGPs,
    author = {Rudner, Tim G. J. and Sejdinovic, Dino and Gal, Yarin},
    title = {{I}nter-domain {D}eep {G}aussian {P}rocesses},
    booktitle = {Proceedings of the 37th International Conference on Machine Learning},
    year = {2020},
    volume = {119},
    series = {Proceedings of Machine Learning Research},
    address = {Online},
    publisher = {PMLR},
}

Reinforcement Learning

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

Cong Lu*, Philip J. Ball*, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh

Preprint. 2022.

RSS '22 Workshop on Learning from Diverse, Offline Data. 2022. (Outstanding Paper Award)

ICML '22 Workshop on Decision Awareness in Reinforcement Learning. 2022.

arXiv Code Bibtex

@inproceedings{
    Lu2022challenges,
    title={{C}hallenges and {O}pportunities in {O}ffline {R}einforcement {L}earning from {V}isual {O}bservations},
    author={Cong Lu and Philip J. Ball and Tim G. J. Rudner and Jack Parker-Holder and Michael A. Osborne and Yee Whye Teh},
    year = {2022},
    eprint = {arXiv:2206.04779},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

Outcome-Driven Reinforcement Learning via Variational Inference

Tim G. J. Rudner*, Vitchyr H. Pong*, Rowan McAllister, Yarin Gal, Sergey Levine

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Website Talk Slides Poster Bibtex

@InProceedings{rudner2021odrl,
    title = {{O}utcome-{D}riven {R}einforcement {L}earning via {V}ariational {I}nference},
    author={Tim G. J. Rudner and Vitchyr H. Pong and Rowan McAllister and Yarin Gal and Sergey Levine},
    journal = {Advances in Neural Information Processing Systems 34},
    year = {2021},
}

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Tim G. J. Rudner*, Cong Lu*, Michael A. Osborne, Yarin Gal, Yee Whye Teh

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Code Website Talk Slides Poster Bibtex

@InProceedings{rudner2020pathologies,
    title = {{O}n {P}athologies in {KL}-{R}egularized {R}einforcement {L}earning from {E}xpert {D}emonstrations},
    author={Tim G. J. Rudner and Cong Lu and Michael A. Osborne and Yarin Gal and Yee Whye Teh},
    journal = {Advances in Neural Information Processing Systems 34},
    year = {2021},
}

VIREL: A Variational Inference Framework for Reinforcement Learning

Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson

NeurIPS '19 Conference on Neural Information Processing Systems. 2019. (Spotlight Talk)

arXiv Code Bibtex

@InProceedings{Fellows2019Virel,
    author = {Fellows, Matthew and Mahajan, Anuj and Rudner, Tim G. J. and Whiteson, Shimon},
    title = {{VIREL}: {A} {V}ariational {I}nference {F}ramework for {R}einforcement {L}earning},
    journal = {Advances in Neural Information Processing Systems 32},
    year = {2019},
    Arxiv = {https://arxiv.org/abs/1811.01132}
}

Reliable Uncertainty Quantification in Deep Learning

Plex: Towards Reliability Using Pretrained Large Model Extensions

Dustin Tran, Jeremiah 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

Preprint. 2022.

ICML '22 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward. 2022. (Contributed Talk)

ICML '22 Workshop on Principles of Distribution Shift. 2022.

arXiv Code Talk Blog Bibtex

@InProceedings{Tran2021plex,
    author = {Dustin Tran and Jeremiah Liu and Michael W. Dusenberry and Du Phan and Mark Collier and Jie Ren and Kehang Han and Zi Wang and Zelda Mariet and Huiyi Hu and Neil Band and Tim G. J. Rudner and Karan Singhal and Zachary Nado and Joost van Amersfoort andAndreas Kirsch and Rodolphe Jenatton and Nithum Thain and Honglin Yuan and Kelly Buchanan and Kevin Murphy and D. Sculley and Yarin Gal and Zoubin Ghahramani and Jasper Snoek and Balaji Lakshminarayanan},
    title = {{P}lex: {T}owards {R}eliability {U}sing {P}retrained {L}arge {M}odel {E}xtensions},
    year = {2022},
    conference = {ICML 2022 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward},
    year = {2022},
    url = {https://goo.gle/plex-paper}
}

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

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

Technical Report. 2022.

NeurIPS '21 Workshop on Bayesian Deep Learning. 2021.

arXiv Code Blog Bibtex

@InProceedings{Nado2021UncertaintyBaselines,
    author = {Zachary Nado and Neil Band and Mark Collier and Josip Djolonga and Michael W. Dusenberry and Sebastian Farquhar and Angelos Filos and Marton Havasi and Rodolphe Jenatton and Ghassen Jerfel and Jeremiah Liu and Zelda Mariet and Jeremy Nixon and Shreyas Padhy and Jie Ren and Tim G. J. Rudner and Yeming Wen and Florian Wenzel and Kevin Murphy and D. Sculley and Balaji Lakshminarayanan and Jasper Snoek and Yarin Gal and Dustin Tran},
    title = {{U}ncertainty {B}aselines: {B}enchmarks {f}or {U}ncertainty {&} {R}obustness {i}n {D}eep {L}earning},
    year = {2021},
    eprint = {arXiv:2106.04015},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Neil Band*, Tim G. J. Rudner*, Qixuan Feng, Angelos Filos, Zachary Nado,
Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Code Poster Bibtex

@InProceedings{
    Band2021benchmarking,
    title={{B}enchmarking {B}ayesian {D}eep {L}earning {o}n {D}iabetic {R}etinopathy {D}etection {T}asks},
    author={Neil Band and Tim G. J. Rudner and Qixuan Feng and Angelos Filos and Zachary Nado and Michael W. Dusenberry and Ghassen Jerfel and Dustin Tran and Yarin Gal},
    journal = {Advances in Neural Information Processing Systems 34},
    year={2021},
}

Non-Technical Papers

Key Concepts in AI Safety: Specification in Machine Learning

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Media Bibtex

@article{rudner2021specification,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {S}pecification in {M}achine {L}earning},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-specification-in-machine-learning/}
}

Key Concepts in AI Safety: Interpretability in Machine Learning

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021interpretability,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {I}nterpretability in {M}achine {L}earning},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-interpretability-in-machine-learning}
}

Key Concepts in AI Safety: Robustness and Adversarial Examples

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021robustness,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {R}obustness and {A}dversarial {E}xamples},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-robustness-and-adversarial-examples}
}

Key Concepts in AI Safety: An Overview

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021aisafety,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {A}n {O}verview},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-an-overview}
}

OECD Framework for the Classification of AI systems

OECD (contributing author: Tim G. J. Rudner)

OECD Publishing. 2022.

Paper Bibtex

@article{oecd2022classification,
   author = "OECD",
   title = "OECD Framework for the Classification of AI systems",
   year = "2022",
   number = "323", 
   url = "https://www.oecd-ilibrary.org/content/paper/cb6d9eca-en",
   doi = "https://doi.org/https://doi.org/10.1787/cb6d9eca-en" 
}

Preprints

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

Cong Lu*, Philip J. Ball*, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh

Preprint. 2022.

RSS '22 Workshop on Learning from Diverse, Offline Data. 2022. (Outstanding Paper Award)

ICML '22 Workshop on Decision Awareness in Reinforcement Learning. 2022.

arXiv Code Bibtex

@inproceedings{
    Lu2022challenges,
    title={{C}hallenges and {O}pportunities in {O}ffline {R}einforcement {L}earning from {V}isual {O}bservations},
    author={Cong Lu and Philip J. Ball and Tim G. J. Rudner and Jack Parker-Holder and Michael A. Osborne and Yee Whye Teh},
    year = {2022},
    eprint = {arXiv:2206.04779},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

Plex: Towards Reliability Using Pretrained Large Model Extensions

Preprint. 2022.

ICML '22 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward. 2022. (Contributed Talk)

ICML '22 Workshop on Principles of Distribution Shift. 2022.

arXiv Code Talk Blog Bibtex

@InProceedings{Tran2021plex,
    author = {Dustin Tran and Jeremiah Liu and Michael W. Dusenberry and Du Phan and Mark Collier and Jie Ren and Kehang Han and Zi Wang and Zelda Mariet and Huiyi Hu and Neil Band and Tim G. J. Rudner and Karan Singhal and Zachary Nado and Joost van Amersfoort andAndreas Kirsch and Rodolphe Jenatton and Nithum Thain and Honglin Yuan and Kelly Buchanan and Kevin Murphy and D. Sculley and Yarin Gal and Zoubin Ghahramani and Jasper Snoek and Balaji Lakshminarayanan},
    title = {{P}lex: {T}owards {R}eliability {U}sing {P}retrained {L}arge {M}odel {E}xtensions},
    year = {2022},
    conference = {ICML 2022 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward},
    year = {2022},
    url = {https://goo.gle/plex-paper}
}

2022

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Tim G. J. Rudner*, Zonghao Chen*, Yee Whye Teh, Yarin Gal

NeurIPS '22 Conference on Neural Information Processing Systems. 2022.

Paper Bibtex

@inproceedings{
    Rudner2022fsvi,
    title={{T}ractabe {F}unction-{S}pace {V}ariational {I}nference in {B}ayesian {N}eural {N}etworks},
    author={Tim G. J. Rudner and Zonghao Chen and Yee Whye Teh and Yarin Gal},
    journal = {Advances in Neural Information Processing Systems 35},
    year = {2022},
}

Continual Learning via Sequential Function-Space Variational Inference

Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal

ICML '22 International Conference on Machine Learning. 2022.

Paper Code Talk Slides Bibtex

@InProceedings{Rudner2021sfsvi,
    author={Tim G. J. Rudner and Freddie Bickford Smith and Qixuan Feng and Yee Whye Teh and Yarin Gal},
    title={{C}ontinual {L}earning via {S}equential {F}unction-{S}pace {V}ariational {I}nference},
    booktitle = {Proceedings of the 38th International Conference on Machine Learning},
    year = {2022},
    series = {Proceedings of Machine Learning Research},
    publisher = {PMLR},
}

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

Technical Report. 2022.

NeurIPS '21 Workshop on Bayesian Deep Learning. 2021.

arXiv Code Blog Bibtex

@InProceedings{Nado2021UncertaintyBaselines,
    author = {Zachary Nado and Neil Band and Mark Collier and Josip Djolonga and Michael W. Dusenberry and Sebastian Farquhar and Angelos Filos and Marton Havasi and Rodolphe Jenatton and Ghassen Jerfel and Jeremiah Liu and Zelda Mariet and Jeremy Nixon and Shreyas Padhy and Jie Ren and Tim G. J. Rudner and Yeming Wen and Florian Wenzel and Kevin Murphy and D. Sculley and Balaji Lakshminarayanan and Jasper Snoek and Yarin Gal and Dustin Tran},
    title = {{U}ncertainty {B}aselines: {B}enchmarks {f}or {U}ncertainty {&} {R}obustness {i}n {D}eep {L}earning},
    year = {2021},
    eprint = {arXiv:2106.04015},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

2021

Outcome-Driven Reinforcement Learning via Variational Inference

Tim G. J. Rudner*, Vitchyr H. Pong*, Rowan McAllister, Yarin Gal, Sergey Levine

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Website Talk Slides Poster Bibtex

@InProceedings{rudner2021odrl,
    title = {{O}utcome-{D}riven {R}einforcement {L}earning via {V}ariational {I}nference},
    author={Tim G. J. Rudner and Vitchyr H. Pong and Rowan McAllister and Yarin Gal and Sergey Levine},
    journal = {Advances in Neural Information Processing Systems 34},
    year = {2021},
}

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Tim G. J. Rudner*, Cong Lu*, Michael A. Osborne, Yarin Gal, Yee Whye Teh

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Code Website Talk Slides Poster Bibtex

@InProceedings{rudner2020pathologies,
    title = {{O}n {P}athologies in {KL}-{R}egularized {R}einforcement {L}earning from {E}xpert {D}emonstrations},
    author={Tim G. J. Rudner and Cong Lu and Michael A. Osborne and Yarin Gal and Yee Whye Teh},
    journal = {Advances in Neural Information Processing Systems 34},
    year = {2021},
}

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Neil Band*, Tim G. J. Rudner*, Qixuan Feng, Angelos Filos, Zachary Nado,
Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal

NeurIPS '21 Conference on Neural Information Processing Systems. 2021.

Paper Code Poster Bibtex

@InProceedings{
    Band2021benchmarking,
    title={{B}enchmarking {B}ayesian {D}eep {L}earning {o}n {D}iabetic {R}etinopathy {D}etection {T}asks},
    author={Neil Band and Tim G. J. Rudner and Qixuan Feng and Angelos Filos and Zachary Nado and Michael W. Dusenberry and Ghassen Jerfel and Dustin Tran and Yarin Gal},
    journal = {Advances in Neural Information Processing Systems 34},
    year={2021},
}

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

Tim G. J. Rudner*, Oscar Key*, Yarin Gal, Tom Rainforth

ICML '21 International Conference on Machine Learning. 2021.

arXiv Code Talk Slides Poster Bibtex

@InProceedings{rudner2021SNRIssuesInDGPs,
    author = {Tim G. J. Rudner and Oscar Key and Yarin Gal and Tom Rainforth},
    title = {{O}n {S}ignal-to-{N}oise {R}atio {I}ssues in {V}ariational {I}nference for {D}eep {G}aussian {P}rocesses},
    booktitle = {Proceedings of the 38th International Conference on Machine Learning},
    year = {2021},
    series = {Proceedings of Machine Learning Research},
    address = {Online},
    publisher = {PMLR},
}

2020

Inter-domain Deep Gaussian Processes

Tim G. J. Rudner, Dino Sejdinovic, Yarin Gal

ICML '20 International Conference on Machine Learning. 2020.

arXiv Website Talk Slides Bibtex

@InProceedings{rudner2020InterDomainDGPs,
    author = {Rudner, Tim G. J. and Sejdinovic, Dino and Gal, Yarin},
    title = {{I}nter-domain {D}eep {G}aussian {P}rocesses},
    booktitle = {Proceedings of the 37th International Conference on Machine Learning},
    year = {2020},
    volume = {119},
    series = {Proceedings of Machine Learning Research},
    address = {Online},
    publisher = {PMLR},
}

2019

VIREL: A Variational Inference Framework for Reinforcement Learning

Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson

NeurIPS '19 Conference on Neural Information Processing Systems. 2019. (Spotlight Talk)

arXiv Code Bibtex

@InProceedings{Fellows2019Virel,
    author = {Fellows, Matthew and Mahajan, Anuj and Rudner, Tim G. J. and Whiteson, Shimon},
    title = {{VIREL}: {A} {V}ariational {I}nference {F}ramework for {R}einforcement {L}earning},
    journal = {Advances in Neural Information Processing Systems 32},
    year = {2019},
    Arxiv = {https://arxiv.org/abs/1811.01132}
}

The Natural Neural Tangent Kernel: Neural Network Training Dynamics under Natural Gradient Descent

Tim G. J. Rudner, Florian Wenzel, Yee Whye Teh, Yarin Gal

NeurIPS '19 Workshop on Bayesian Deep Learning. 2019. (Contributed Talk)

Paper Talk Bibtex

@article{rudner2019NaturalNTK,
    author = {Rudner, Tim G. J. and Wenzel, Florian and Yee Whye Teh and Gal, Yarin},
    title = {{T}he {N}atural {N}eural {T}angent {K}ernel: {N}eural {N}etwork {T}raining {D}ynamics {u}nder {N}atural {G}radient {D}escent},
    journal = {4{th} {W}orkshop {o}n {B}ayesian {D}eeep {L}earning ({NeurIPS} 2019)},
    year = {2019},
}

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

Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G. J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh,
Arnoud de Kroon, Yarin Gal

Technical Report. 2019.

NeurIPS '19 Workshop on Bayesian Deep Learning. 2019.

arXiv Code Bibtex

@InProceedings{Filos2019bdlb,
    author = {Angelos Filos and Sebastian Farquhar and Aidan N. Gomez and Tim G. J. Rudner and Zachary Kenton and Lewis Smith and Milad Alizadeh and Arnoud de Kroon and Yarin Gal},
    title = {{A} {S}ystematic {C}omparison {o}f {B}ayesian {D}eep {L}earning {R}obustness in {D}iabetic {R}etinopathy {T}asks},
    year = {2019},
    eprint = {1912.10481},
    archivePrefix={arXiv},
    primaryClass={stat.ML}
}

Multi³Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery

Tim G. J. Rudner, Marc Rußwurm, Jakub Fil, Ramona Pelich, Benjamin Bischke, Veronika Kopackova, Piotr Bilinski

AAAI '19 Conference on Artificial Intelligence. 2019.

arXiv Code Media Bibtex

@InProceedings{rudner2019Multi3Net,
    author = {Rudner, Tim G. J. and Rußwurm, Marc and Fil, Jakub and Pelich, Ramona and Bischke, Benjamin and Kopackova, Veronika and Bilinski, Piotr},
    title = {{M}ulti{$^3$}{N}et: {S}egmenting {F}looded {B}uildings via {F}usion of {M}ultiresolution, {M}ultisensor, and {M}ultitemporal {S}atellite {I}magery},
    journal = {Proceedings of the Thirty-Three {AAAI} Conference on Artificial Intelligence},
    year = {2019},
    Arxiv = {https://arxiv.org/abs/1812.01756}
}

The StarCraft Multi-Agent Challenge

Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli,
Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foerster, Shimon Whiteson

AAMAS '19 International Conference on Autonomous Agents and Multiagent Systems. 2019.

arXiv Code Bibtex

@article{Samvelyan19Smac,
    author = {Samvelyan, Mikayel and Rashid, Tabish and Schroeder de Witt, Christian and Farquhar, Gregory and Nardelli, Nantas and Rudner, Tim G. J. and Hung, Chia-Man and Torr, Philip H. S. and Foerster, Jakob and Whiteson, Shimon},
    title = {{T}he {S}tar{C}raft {M}ulti-{A}gent {C}hallenge},
    journal = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},
    year = {2019},
    Arxiv = {https://arxiv.org/abs/1902.04043}
}

2018

On the Connection between Neural Processes and Gaussian Processes with Deep Kernels

Tim G. J. Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal

NeurIPS '18 Workshop on Bayesian Deep Learning. 2018.

Paper Bibtex

@article{rudner2018NPsasGPs,
    author = {Rudner, Tim G. J. and Fortuin, Vincent and Teh, Yee Whye and Gal, Yarin},
    title = {{O}n the {C}onnection between {N}eural {P}rocesses and {G}aussian {P}rocesses with {D}eep {K}ernels},
    conference = {NeurIPS 2018 Workshop on Bayesian Deep Learning},
    year = {2018},
    url = {http://bayesiandeeplearning.org/2018/papers/128.pdf}
}

Non-Technical Papers

Key Concepts in AI Safety: Specification in Machine Learning

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Media Bibtex

@article{rudner2021specification,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {S}pecification in {M}achine {L}earning},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-specification-in-machine-learning/}
}

Key Concepts in AI Safety: Interpretability in Machine Learning

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021interpretability,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {I}nterpretability in {M}achine {L}earning},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-interpretability-in-machine-learning}
}

Key Concepts in AI Safety: Robustness and Adversarial Examples

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021robustness,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {R}obustness and {A}dversarial {E}xamples},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-robustness-and-adversarial-examples}
}

Key Concepts in AI Safety: An Overview

Tim G. J. Rudner and Helen Toner

CSET Issue Briefs. 2021.

Paper Bibtex

@article{rudner2021aisafety,
    author = {Rudner, Tim G. J. and Toner, Helen},
    title = {{K}ey {C}oncepts in {AI} {S}afety: {A}n {O}verview},
    conference = {CSET Issue Briefs},
    year = {2021},
    url = {https://cset.georgetown.edu/publication/key-concepts-in-ai-safety-an-overview}
}

OECD Framework for the Classification of AI systems

OECD (contributing author: Tim G. J. Rudner)

OECD Publishing. 2022.

Paper Bibtex

@article{oecd2022classification,
   author = "OECD",
   title = "OECD Framework for the Classification of AI systems",
   year = "2022",
   number = "323", 
   url = "https://www.oecd-ilibrary.org/content/paper/cb6d9eca-en",
   doi = "https://doi.org/https://doi.org/10.1787/cb6d9eca-en" 
}

Teaching (Past & Present)

Lecturer: Bayesian Machine Learning, Courant Institute of Mathematical Sciences, New York University
Lecturer: Data, Estimation, and Inference (Part 1, Part 2), Department of Engineering Science, University of Oxford
Teaching Assistant: Advanced Topics in Machine Learning, Department of Computer Science, University of Oxford
Teaching Assistant: Applied Statistics (Part 1, Part 2), Department of Statistics, University of Oxford
Teaching Assistant: Statistics, Department of Statistics, University of Oxford