Daniel Jarrett

Note: As of April 2023, I have joined Google DeepMind full time as Research Scientist.

I am a final-year Ph.D. candidate in Mathematics at the University of Cambridge, advised by Mihaela van der Schaar in the Machine Learning and Artificial Intelligence group. Presently at Google DeepMind as research scientist intern, hosted by Corentin Tallec and Michal Valko in the Deep Reinforcement Learning team, studying representation learning and exploration.

Research interests include generative modeling, reinforcement learning, and causal inference, focusing on modeling, understanding, and improving decision-making over time. Prior stints: investment banking, economic research, and software engineering. I hold an M.S. Computer Science from University of Oxford and B.A. Economics (Finance) from Princeton University.

[LinkedIn] [Scholar] [Faculty] [Group]

* Equal contribution

Conference

Accountability in Offline Learning: Explaining Decisions with a Corpus of Examples.
Neural Information Processing Systems (NeurIPS), 2023.
H. Sun, A. Hüyük, D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems.
Neural Information Processing Systems (NeurIPS), 2023.
J. Berrevoets, D. Jarrett, A. Chan, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments.
International Conference on Machine Learning (ICML), 2023.
D. Jarrett, C. Tallec, F. Altché, T. Mesnard, R. Munos, M. Valko.
[Abstract] [Bibtex] [Entry] [Paper]

Online Decision Mediation.
Neural Information Processing Systems (NeurIPS), 2022.
D. Jarrett, A. Hüyük, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

HyperImpute: Generalized Iterative Imputation with Automatic Model Selection.
International Conference on Machine Learning (ICML), 2022.
D. Jarrett*, B. Cebere*, T. Liu, A. Curth, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Inverse Contextual Bandits: Learning How Behavior Evolves over Time.
International Conference on Machine Learning (ICML), 2022.
A. Hüyük*, D. Jarrett*, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Time-series Generation by Contrastive Imitation.
Neural Information Processing Systems (NeurIPS), 2021.
D. Jarrett, I. Bica, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Invariant Causal Imitation Learning for Generalizable Policies.
Neural Information Processing Systems (NeurIPS), 2021.
I. Bica*, D. Jarrett*, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Medkit-Learn Environment: Medical Decision Modeling through Simulation.
Neural Information Processing Systems (NeurIPS), 2021.
A. Chan, I. Bica, A. Hüyük, D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Closing the Loop in Medical Decision Support: A Case Study on Organ Transplantation.
Neural Information Processing Systems (NeurIPS), 2021.
Y. Qin, F. Imrie, A. Hüyük, D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Inverse Decision Modeling: Learning Interpretable Representations of Behavior.
International Conference on Machine Learning (ICML), 2021.
D. Jarrett*, A. Hüyük*, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Clairvoyance: A Pipeline Toolkit for Medical Time Series.
International Conference on Learning Representations (ICLR), 2021.
D. Jarrett*, J. Yoon*, I. Bica, Z. Qian, A. Ercole, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning.
International Conference on Learning Representations (ICLR), 2021.
A. Hüyük*, D. Jarrett*, C. Tekin, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Learning "What-If" Explanations for Sequential Decision-Making.
International Conference on Learning Representations (ICLR), 2021.
I. Bica, D. Jarrett, A. Hüyük, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Strictly Batch Imitation Learning by Energy-based Distribution Matching.
Neural Information Processing Systems (NeurIPS), 2020.
D. Jarrett*, I. Bica*, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Hide-and-Seek Privacy Challenge.
Neural Information Processing Systems (NeurIPS), 2020.
J. Jordon, D. Jarrett, E. Saveliev, ..., D. Belgrave, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Inverse Active Sensing: Modeling and Understanding Timely Decision-Making.
International Conference on Machine Learning (ICML), 2020.
D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning.
Artificial Intelligence and Statistics (AISTATS), 2020.
Y. Zhang, D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Target-Embedding Autoencoders for Supervised Representation Learning.
International Conference on Learning Representations (ICLR), 2020.
D. Jarrett, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Time-series Generative Adversarial Networks.
Neural Information Processing Systems (NeurIPS), 2019.
J. Yoon*, D. Jarrett*, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Workshop

Language Agents as Digital Representatives in Collective Decision-Making.
Foundation Models for Decision Making Workshop (NeurIPS), 2023.
D. Jarrett*, M. Pîslar*, ..., R. Elie, C. Summerfield, A. Tacchetti.
[Abstract] [Bibtex] [Entry] [Paper]

Curiosity in Hindsight.
Deep Reinforcement Learning Workshop (NeurIPS), 2022.
D. Jarrett, C. Tallec, F. Altché, T. Mesnard, R. Munos, M. Valko.
[Abstract] [Bibtex] [Entry] [Paper]

Match-Net: Dynamic Prediction in Survival Analysis using Convolutional Networks.
Machine Learning for Health Workshop (NeurIPS), 2018.
D. Jarrett, J. Yoon, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Journal

How AI and ML can Help Healthcare Systems Respond to COVID-19.
Machine Learning (Mach. Learn.), 2021.
M. van der Schaar, A. Alaa, ..., D. Jarrett, Pietro Lio, Ari Ercole.
[Abstract] [Bibtex] [Entry] [Paper]

Predicting Clinical Trajectories using Automated Longitudinal Model Selection.
Pediatric Pulmonology (Pediatr. Pulmonol.), 2020.
Y. Zhang, D. Jarrett, A. Floto, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Applications and Limitations of Machine Learning in Radiation Oncology.
The British Journal of Radiology (BJR), 2019.
D. Jarrett, E. Stride, K. Vallis, M. J. Gooding.
[Abstract] [Bibtex] [Entry] [Paper]

Dynamic Prediction in Clinical Survival Analysis using Temporal Convolutions.
IEEE Journal of Biomedical and Health Informatics (JBHI), 2019.
D. Jarrett, J. Yoon, M. van der Schaar.
[Abstract] [Bibtex] [Entry] [Paper]

Thesis

Advances in Reinforcement Learning for Decision Support.
Faculty of Mathematics, University of Cambridge, 2023.
D. Jarrett.
[Abstract] [Bibtex] [Entry] [Paper]

Press

2023 InstaDeep AI, Curious Agents, Part IV: BYOL-Hindsight.
2023 DeepMind Research Blog, Curiosity in Hindsight.
2022 Applied Artificial Intelligence, Machine Learning for Algorithmic Trading.
2022 Hachette Book Group, What We Owe The Future.
2022 van der Schaar Lab, Data Imputation in Machine Learning.
2021 Less Wrong, Learning Human Intent.
2021 Towards Data Science, Modeling and Generating Time-Series Data.
2021 Alignment Newsletter Podcast, Collaborating with Humans without Human Data.
2021 Towards Data Science, Synthetic Time-Series Data: A GAN Approach.
2021 van der Schaar Lab, Time Series in Healthcare.
2020 Neptune AI, Best Deep Learning Papers from the ICLR 2020 Conference.

Reviewing

Neural Information Processing Systems (NeurIPS).
International Conference on Machine Learning (ICML).
International Conference on Learning Representations (ICLR).

Teaching

Artificial Intelligence (COMS W4701, CSMM 101x), Columbia University.
Microeconomic Theory: A Mathematical Approach (ECO 310), Princeton University.
New Analyst and Associate Training (SAS, SQL, VBA), Cornerstone Research.