Jake Snell

jcs241@cam.ac.uk

Incoming Assistant Professor (Jan 2027)
Machine Learning Group
Computational and Biological Learning Lab
Department of Engineering
University of Cambridge

I am an incoming Assistant Professor in the Department of Engineering at the University of Cambridge. I work on building trustworthy deep learning algorithms through the perspective of probabilistic modeling. My research interests include:

designing learning algorithms with stronger generalization capabilities,
developing statistical methods to ensure the reliability of AI in high-risk settings, and
devising procedures to automatically assess the limitations of AI systems and understand their behavior.

Before joining Cambridge as faculty, I was an Associate Research Scholar at Princeton Computer Science. I received my Master's (2014) and PhD (2021) in Computer Science from the University of Toronto and my Bachelor's (2010) from Yale.

Interested in joining my research group? See information for prospective PhD and Master's students.

Teaching

4M26: Algorithms and Data Structures (Lent 2027)
2P8: Information Engineering (Easter 2027)

Publications

For a fully up-to-date list, see my Google Scholar page.

Conformal Prediction as Bayesian Quadrature

Jake C. Snell, Thomas L. Griffiths
International Conference on Machine Learning (ICML), 2025.
🏆 Outstanding Paper Award
paper / code / poster

Binary Climate Data Visuals Amplify Perceived Impact of Climate Change

Grace Liu, Jake C. Snell, Thomas L. Griffiths, Rachit Dubey
Nature Human Behaviour, 2025.
paper

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

Jake C. Snell, Gianluca M. Bencomo, Thomas L. Griffiths
Neural Information Processing Systems (NeurIPS), 2024.
paper / code / poster

Improving Predictor Reliability with Selective Recalibration

Thomas P. Zollo, Zhun Deng, Jake C. Snell, Toniann Pitassi, Richard Zemel
Transactions on Machine Learning Research (TMLR), 2024.
paper / code

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths
International Conference on Learning Representations (ICLR), 2024.
paper / code

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models

Thomas P. Zollo, Todd Morrill, Zhun Deng, Jake C. Snell, Toniann Pitassi, Richard Zemel
International Conference on Learning Representations (ICLR), 2024.
paper

Distribution-Free Statistical Dispersion Control for Societal Applications

Zhun Deng, Thomas P. Zollo, Jake C. Snell, Toniann Pitassi, Richard Zemel
Neural Information Processing Systems (NeurIPS), 2023.
Spotlight
paper

Im-Promptu: In-Context Composition from Image Prompts

Bhishma Dedhia, Michael Chang, Jake C. Snell, Thomas L. Griffiths, Niraj K. Jha
Neural Information Processing Systems (NeurIPS), 2023.
paper / code / project page

Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions

Jake C. Snell, Thomas P. Zollo, Zhun Deng, Toniann Pitassi, Richard Zemel
International Conference on Learning Representations (ICLR), 2023.
paper / code

Learning to Build Probabilistic Models with Limited Data

Jake C. Snell
Ph.D. Thesis, Department of Computer Science, University of Toronto, 2021.
thesis

Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes

Jake C. Snell, Richard Zemel
International Conference on Learning Representations (ICLR), 2021.
paper / arxiv extended version / code

Lorentzian Distance Learning for Hyperbolic Representations

Marc T. Law, Renjie Liao, Jake Snell, Richard S. Zemel
International Conference on Machine Learning (ICML), 2019.
paper / retrieval code / classification code

Dimensionality Reduction for Representing the Knowledge of Probabilistic Models

Marc T. Law, Jake Snell, Amir-massoud Farahmand, Raquel Urtasun, Richard S. Zemel
International Conference on Learning Representations (ICLR), 2019.
paper / visualization code / flowers zero-shot code / CUB zero-shot code

Learning Latent Subspaces in Variational Autoencoders

Jack Klys, Jake Snell, Richard Zemel
Neural Information Processing Systems (NeurIPS), 2018.
paper

Meta-learning for Semi-supervised Few-shot Classification

Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel
International Conference on Learning Representations (ICLR), 2018.
paper / code

Prototypical Networks for Few-shot Learning

Jake C. Snell, Kevin Swersky, Richard Zemel
Neural Information Processing Systems (NeurIPS), 2017.
paper / code

Learning to Generate Images With Perceptual Similarity Metrics

Jake Snell, Karl Ridgeway, Renjie Liao, Brett D. Roads, Michael C. Mozer, Richard S. Zemel
IEEE International Conference on Image Processing (ICIP), 2017.
Finalist for Best Student Paper Award
paper / supplementary

Stochastic Segmentation Trees for Multiple Ground Truths

Jake Snell, Richard S. Zemel
Uncertainty in Artificial Intelligence (UAI), 2017.
paper / supplementary