Pith. sign in

REVIEW 1 cited by

Neural Networks with Cheap Differential Operators

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.03579 v1 pith:YBEIPUNK submitted 2019-12-08 cs.LG stat.ML

Neural Networks with Cheap Differential Operators

classification cs.LG stat.ML
keywords differentialoperatorsneuralarchitecturecheapcomputationderivativesdimension-wise
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise derivatives, used in cases such as computing the divergence. Our proposed architecture has a Jacobian matrix composed of diagonal and hollow (non-diagonal) components. We can then modify the backward computation graph to extract dimension-wise derivatives efficiently with automatic differentiation. We demonstrate these cheap differential operators for solving root-finding subproblems in implicit ODE solvers, exact density evaluation for continuous normalizing flows, and evaluating the Fokker--Planck equation for training stochastic differential equation models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Analytic Bijections for Smooth and Interpretable Normalizing Flows

    cs.LG 2026-01 conditional novelty 6.0

    Three new analytic bijections and a radial flow architecture give globally smooth, closed-form invertible normalizing flows that match or beat spline baselines on benchmarks and improve phi^4 lattice-field sampling.