Will Grathwohl
Will Grathwohl
Verifierad e-postadress på cs.toronto.edu - Startsida
Citeras av
Citeras av
Ffjord: Free-form continuous dynamics for scalable reversible generative models
W Grathwohl, RTQ Chen, J Bettencourt, I Sutskever, D Duvenaud
arXiv preprint arXiv:1810.01367, 2018
Invertible residual networks
J Behrmann, W Grathwohl, RTQ Chen, D Duvenaud, JH Jacobsen
International Conference on Machine Learning, 573-582, 2019
Backpropagation through the void: Optimizing control variates for black-box gradient estimation
W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud
arXiv preprint arXiv:1711.00123, 2017
Your classifier is secretly an energy based model and you should treat it like one
W Grathwohl, KC Wang, JH Jacobsen, D Duvenaud, M Norouzi, ...
arXiv preprint arXiv:1912.03263, 2019
Deep reinforcement learning and simulation as a path toward precision medicine
BK Petersen, J Yang, WS Grathwohl, C Cockrell, C Santiago, G An, ...
Journal of Computational Biology 26 (6), 597-604, 2019
Understanding the limitations of conditional generative models
E Fetaya, JH Jacobsen, W Grathwohl, R Zemel
arXiv preprint arXiv:1906.01171, 2019
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
W Grathwohl, KC Wang, JH Jacobsen, D Duvenaud, R Zemel
International Conference on Machine Learning, 2020
Disentangling space and time in video with hierarchical variational auto-encoders
W Grathwohl, A Wilson
arXiv preprint arXiv:1612.04440, 2016
Gradient-based optimization of neural network architecture
W Grathwohl, E Creager, SKS Ghasemipour, R Zemel
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
W Grathwohl, J Kelly, M Hashemi, M Norouzi, K Swersky, D Duvenaud
arXiv preprint arXiv:2010.04230, 2020
Joint energy-based models for semi-supervised classification
S Zhao, JH Jacobsen, W Grathwohl
ICML Workshop on Uncertainty and Robustness in Deep Learning, 2020
Training Glow with constant memory cost
X Li, W Grathwohl
NIPS Workshop on Bayesian Deep Learning, 2018
Few-shot learning for free by modelling global class structure
X Li, W Grathwohl, E Triantafillou, D Duvenaud, R Zemel
2nd Workshop on Meta-Learning at NeurIPS, 2018
Using digital ultrasound to investigate trill vibration.
DH Whalen, K Iskarous, W Grathwohl, M Proctor
The Journal of the Acoustical Society of America 128 (4), 2289-2289, 2010
No Conditional Models for me: Training Joint EBMs on Mixed Continuous and Discrete Data
J Kelly, WS Grathwohl
Energy Based Models Workshop-ICLR 2021, 2021
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
W Grathwohl, K Swersky, M Hashemi, D Duvenaud, CJ Maddison
arXiv preprint arXiv:2102.04509, 2021
Your classifier is secretly an energy based model and you should treat it like one
D Duvenaud, J Wang, J Jacobsen, K Swersky, M Norouzi, W Grathwohl
Design Motifs for Probabilistic Generative Design
G Roeder, N Killoran, W Grathwohl, D Duvenaud
Deep Reinforcement Learning and Simulation as a Path Toward Precision Medicine Download PDF
BK Petersen, J Yang, WS Grathwohl, C Cockrell, C Santiago, G An, ...
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–19