216 citations · 510 across the 17 of their papers we have counts for
18 papers
Decomposing reverse-mode automatic differentiation
Roy Frostig, Matthew J. Johnson, Dougal Maclaurin +2
We decompose reverse-mode automatic differentiation into (forward-mode) linearization followed by transposition. Doing so isolates the essential difference between forward- and rev…
Learning Differential Equations that are Easy to Solve
Jacob Kelly, Jesse Bettencourt, Matthew James Johnson +1
Differential equations parameterized by neural networks become expensive to solve numerically as training progresses. We propose a remedy that encourages learned dynamics to be eas…
Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language
Matthew D. Hoffman, Matthew J. Johnson, Dustin Tran
Deriving conditional and marginal distributions using conjugacy relationships can be time consuming and error prone. In this paper, we propose a strategy for automating such deriva…
The LORACs prior for VAEs: Letting the Trees Speak for the Data
Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
In variational autoencoders, the prior on the latent codes is often treated as an afterthought, but the prior shapes the kind of latent representation that the model learns. If…
Unsteady ballistic heat transport in infinite harmonic crystals
Vitaly A. Kuzkin
We study thermal processes in infinite harmonic crystals having a unit cell with arbitrary number of particles. Initially particles have zero displacements and random velocities, c…
Estimating the Spectral Density of Large Implicit Matrices
Ryan P. Adams, Jeffrey Pennington, Matthew J. Johnson +4
Many important problems are characterized by the eigenvalues of a large matrix. For example, the difficulty of many optimization problems, such as those arising from the fitting of…