Pith. sign in

REVIEW 1 cited by

TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed

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 2203.10335 v2 pith:JFSWG2C7 submitted 2022-03-19 cs.CV

TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed

classification cs.CV
keywords neuraltrainingapproachtemporalbeencontinuousdistributionevolutionary
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Continuous normalizing flows (CNFs) construct invertible mappings between an arbitrary complex distribution and an isotropic Gaussian distribution using Neural Ordinary Differential Equations (neural ODEs). It has not been tractable on large datasets due to the incremental complexity of the neural ODE training. Optimal Transport theory has been applied to regularize the dynamics of the ODE to speed up training in recent works. In this paper, a temporal optimization is proposed by optimizing the evolutionary time for forward propagation of the neural ODE training. In this appoach, we optimize the network weights of the CNF alternately with evolutionary time by coordinate descent. Further with temporal regularization, stability of the evolution is ensured. This approach can be used in conjunction with the original regularization approach. We have experimentally demonstrated that the proposed approach can significantly accelerate training without sacrifying performance over baseline 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. Joint Flow Matching for Generator-Consistent Classification

    cs.LG 2026-07 conditional novelty 5.0

    Assigning images and labels opposite endpoints in a flow gives one model that both generates and classifies, with forward and backward passes sampling from the same joint.