400 citations · 781 across the 13 of their papers we have counts for
4 papers · 1 filter
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
Will Grathwohl, Kuan-Chieh Wang, Jorn-Henrik Jacobsen +2
We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model's log-density. We estim…
Residual Flows for Invertible Generative Modeling
Ricky T. Q. Chen, Jens Behrmann, David Duvenaud +1
Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks prov…
Early Stopping is Nonparametric Variational Inference
Dougal Maclaurin, David Duvenaud, Ryan P. Adams
We show that unconverged stochastic gradient descent can be interpreted as a procedure that samples from a nonparametric variational approximate posterior distribution. This distri…
Gradient-based Hyperparameter Optimization through Reversible Learning
Dougal Maclaurin, David Duvenaud, Ryan P. Adams
Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hype…