Will Grathwohl
Will Grathwohl
Verified email at cs.toronto.edu - Homepage
TitleCited byYear
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
872017
Ffjord: Free-form continuous dynamics for scalable reversible generative models
W Grathwohl, RTQ Chen, J Betterncourt, I Sutskever, D Duvenaud
arXiv preprint arXiv:1810.01367, 2018
852018
Invertible residual networks
J Behrmann, W Grathwohl, RTQ Chen, D Duvenaud, JH Jacobsen
arXiv preprint arXiv:1811.00995, 2018
362018
Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis
BK Petersen, J Yang, WS Grathwohl, C Cockrell, C Santiago, G An, ...
arXiv preprint arXiv:1802.10440, 2018
62018
Disentangling space and time in video with hierarchical variational auto-encoders
W Grathwohl, A Wilson
arXiv preprint arXiv:1612.04440, 2016
62016
Gradient-based optimization of neural network architecture
W Grathwohl, E Creager, SKS Ghasemipour, R Zemel
52018
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
32019
Training Glow with Constant Memory Cost
X Li, W Grathwohl
NIPS Workshop on Bayesian Deep Learning, 2018
12018
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
12010
Design Motifs for Probabilistic Generative Design
G Roeder, N Killoran, W Grathwohl, D Duvenaud
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
2018
The system can't perform the operation now. Try again later.
Articles 1–11