Követés
Jake C. Snell
Jake C. Snell
Postdoctoral Researcher, Princeton University
E-mail megerősítve itt: princeton.edu - Kezdőlap
Cím
Hivatkozott rá
Hivatkozott rá
Év
Prototypical networks for few-shot learning
J Snell, K Swersky, RS Zemel
Advances in Neural Information Processing Systems 30, 4077-4087, 2017
104222017
Meta-learning for semi-supervised few-shot classification
M Ren, E Triantafillou, S Ravi, J Snell, K Swersky, JB Tenenbaum, ...
International Conference on Learning Representations, 2018
17422018
Learning to generate images with perceptual similarity metrics
J Snell, K Ridgeway, R Liao, BD Roads, MC Mozer, RS Zemel
2017 IEEE international conference on image processing (ICIP), 4277-4281, 2017
2302017
Learning latent subspaces in variational autoencoders
J Klys, J Snell, R Zemel
Advances in Neural Information Processing Systems 31, 6444-6454, 2018
1742018
Lorentzian distance learning for hyperbolic representations
M Law, R Liao, J Snell, R Zemel
International Conference on Machine Learning, 3672-3681, 2019
1262019
Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes
J Snell, R Zemel
Ninth International Conference on Learning Representations (ICLR 2021), 2021
762021
Dimensionality reduction for representing the knowledge of probabilistic models
MT Law, J Snell, A Farahmand, R Urtasun, RS Zemel
International Conference on Learning Representations, 2018
152018
Few-Shot Attribute Learning
M Ren, E Triantafillou, KC Wang, J Lucas, J Snell, X Pitkow, AS Tolias, ...
13*2020
Quantile risk control: A flexible framework for bounding the probability of high-loss predictions
JC Snell, TP Zollo, Z Deng, T Pitassi, R Zemel
arXiv preprint arXiv:2212.13629, 2022
82022
Prompt risk control: A rigorous framework for responsible deployment of large language models
TP Zollo, T Morrill, Z Deng, JC Snell, T Pitassi, R Zemel
arXiv preprint arXiv:2311.13628, 2023
72023
Distribution-free statistical dispersion control for societal applications
Z Deng, T Zollo, J Snell, T Pitassi, R Zemel
Advances in Neural Information Processing Systems 36, 40342-40366, 2023
42023
Im-promptu: in-context composition from image prompts
B Dedhia, M Chang, J Snell, T Griffiths, N Jha
Advances in Neural Information Processing Systems 36, 53261-53274, 2023
32023
Stochastic Segmentation Trees for Multiple Ground Truths.
J Snell, RS Zemel
UAI, 2017
32017
A metalearned neural circuit for nonparametric bayesian inference
J Snell, G Bencomo, T Griffiths
Advances in Neural Information Processing Systems 37, 57301-57323, 2024
22024
Implicit maximum a posteriori filtering via adaptive optimization
GM Bencomo, JC Snell, TL Griffiths
arXiv preprint arXiv:2311.10580, 2023
22023
Conformal Prediction as Bayesian Quadrature
JC Snell, TL Griffiths
arXiv preprint arXiv:2502.13228, 2025
2025
Improving Predictor Reliability with Selective Recalibration
TP Zollo, Z Deng, JC Snell, T Pitassi, R Zemel
arXiv preprint arXiv:2410.05407, 2024
2024
Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases
R Marjieh, S Kumar, D Campbell, L Zhang, G Bencomo, J Snell, ...
arXiv preprint arXiv:2405.19420, 2024
2024
Learning to Build Probabilistic Models with Limited Data
JC Snell
University of Toronto (Canada), 2021
2021
Early Exiting in Deep Neural Networks via Dirichlet-based Uncertainty Quantification
F Xia, J Snell, TL Griffiths
NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles …, 0
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–20