no code implementations • 27 Feb 2023 • Francisco Vargas, Will Grathwohl, Arnaud Doucet
Denoising Diffusion Samplers (DDS) are obtained by approximating the corresponding time-reversal.
2 code implementations • 22 Feb 2023 • Yilun Du, Conor Durkan, Robin Strudel, Joshua B. Tenenbaum, Sander Dieleman, Rob Fergus, Jascha Sohl-Dickstein, Arnaud Doucet, Will Grathwohl
In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and guidance.
no code implementations • 28 Nov 2022 • Sander Dieleman, Laurent Sartran, Arman Roshannai, Nikolay Savinov, Yaroslav Ganin, Pierre H. Richemond, Arnaud Doucet, Robin Strudel, Chris Dyer, Conor Durkan, Curtis Hawthorne, Rémi Leblond, Will Grathwohl, Jonas Adler
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement.
no code implementations • 8 Nov 2022 • Robin Strudel, Corentin Tallec, Florent Altché, Yilun Du, Yaroslav Ganin, Arthur Mensch, Will Grathwohl, Nikolay Savinov, Sander Dieleman, Laurent SIfre, Rémi Leblond
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation?
no code implementations • 31 Oct 2022 • Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Sheila Babayan, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
A fundamental ability of an intelligent web-based agent is seeking out and acquiring new information.
1 code implementation • 16 Aug 2022 • Arnaud Doucet, Will Grathwohl, Alexander G. D. G. Matthews, Heiko Strathmann
To obtain an importance sampling estimate of the marginal likelihood, AIS introduces an extended target distribution to reweight the Markov chain proposal.
1 code implementation • 19 Jul 2021 • Jacob Kelly, Richard Zemel, Will Grathwohl
We find our models are capable of both accurate, calibrated predictions and high-quality conditional synthesis of novel attribute combinations.
1 code implementation • 8 Feb 2021 • Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables.
1 code implementation • ICLR 2021 • Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud
Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty.
1 code implementation • ICML 2020 • Will Grathwohl, Kuan-Chieh Wang, Jorn-Henrik Jacobsen, David Duvenaud, Richard Zemel
We estimate the Stein discrepancy between the data density $p(x)$ and the model density $q(x)$ defined by a vector function of the data.
4 code implementations • ICLR 2020 • Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y).
no code implementations • ICLR 2020 • Ethan Fetaya, Jörn-Henrik Jacobsen, Will Grathwohl, Richard Zemel
Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts.
5 code implementations • 2 Nov 2018 • Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen
We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation.
Ranked #5 on Image Generation on MNIST
7 code implementations • ICLR 2019 • Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud
The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
Ranked #1 on Density Estimation on UCI MINIBOONE
7 code implementations • ICLR 2018 • Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud
Gradient-based optimization is the foundation of deep learning and reinforcement learning.
no code implementations • 14 Dec 2016 • Will Grathwohl, Aaron Wilson
In this paper we propose a probabilistic approach for learning separable representations of object identity and pose information using unsupervised video data.