About

I am a postdoc in the Dept. of Computer Science at Princeton University, where I work with Tom Griffiths. I earned my Ph.D. in computer science at U of Toronto, where my advisor was Richard Zemel. Previously, I completed my bachelor's degree in biomedical engineering at Yale.

I work on building trustworthy deep learning algorithms through the perspective of probabilistic modeling. My current research interests include:

1. Robustness. Designing learning algorithms that are robust to new environments and changes over time, with a particular focus on meta-learning and Bayesian filtering.

2. Reliability. Quantifying the reliability of black box models, with an emphasis on distribution-free and nonparametric methods.

3. Transparency. Developing Bayesian inference algorithms to better understand representations and behavior of AI models.

I am on the academic job market for 2024-2025!

News

Apr. 2025: Our Nature Human Behaviour paper is now available.
Jan. 2025: One paper accepted to Nature Human Behaviour.
Sep. 2024: One paper accepted at NeurIPS 2024.
Jul. 2024: One paper accepted at TMLR.
Feb. 2024: Invited talk at Stanford University in the Department of Statistics.
Jan. 2024: Two papers accepted at ICLR 2024.
Sep. 2023: Two papers accepted at NeurIPS 2023.

Mentorship

Current Mentees
Gianluca Bencomo, CS Ph.D. student at Princeton.
Yan (Roger) Weng, CS Undergrad at Princeton.
Liyi Zhang, CS Ph.D. student at Princeton.

Former Mentees
Bhishma Dedhia, ECE Ph.D. student at Princeton.
Grace Liu, CS Master's at Princeton. Now a Ph.D. student at Carnegie Mellon.
Feng (Shelley) Xia, CS Master's at Princeton. Now a machine learning engineer at TikTok.
Tom Zollo, CS Master's at Columbia. Now a Ph.D. student, also at Columbia.

Selected Publications

Thumbnail image for A Metalearned Neural Circuit for Nonparametric Bayesian Inference.

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

Jake C. Snell, Gianluca Bencomo, Thomas L. Griffiths

Neural Information Processing Systems (NeurIPS) 2024.
PDF
Code
poster
Thumbnail image for Implicit Maximum a Posteriori Filtering via Adaptive Optimization.

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths

International Conference on Learning Representations (ICLR) 2024.
PDF
Code
Thumbnail image for Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions.

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.
PDF
Code
Thumbnail image for Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes.

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.
PDF
arXiv
Code
Thumbnail image for Prototypical Networks for Few-shot Learning.

Prototypical Networks for Few-shot Learning

Jake C. Snell, Kevin Swersky, Richard Zemel

Neural Information Processing Systems (NeurIPS) 2017.