Pith. sign in

REVIEW 1 cited by

Acceleration via Symplectic Discretization of High-Resolution Differential Equations

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 1902.03694 v2 pith:UBL4MN7O submitted 2019-02-11 math.OC cs.LGcs.NAmath.NAstat.ML

classification math.OCcs.LGcs.NAmath.NAstat.ML
keywords schemesymplecticacceleratedaccelerationalgorithmdifferentialdiscretizationequations
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We study first-order optimization methods obtained by discretizing ordinary differential equations (ODEs) corresponding to Nesterov's accelerated gradient methods (NAGs) and Polyak's heavy-ball method. We consider three discretization schemes: an explicit Euler scheme, an implicit Euler scheme, and a symplectic scheme. We show that the optimization algorithm generated by applying the symplectic scheme to a high-resolution ODE proposed by Shi et al. [2018] achieves an accelerated rate for minimizing smooth strongly convex functions. On the other hand, the resulting algorithm either fails to achieve acceleration or is impractical when the scheme is implicit, the ODE is low-resolution, or the scheme is explicit.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. On the stability of optimization algorithms given by discretizations of the Euler-Lagrange ODE

    math.OC 2019-08 reject novelty 5.0 of 10

    The iteration-stability bound claimed for the explicit-implicit Euler discretization of the Euler-Lagrange acceleration ODE is not proven and is false for some parameter values permitted by the theorem.

Pith tools