Pith. sign in

REVIEW 3 cited by

Training GANs with Centripetal Acceleration

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1902.08949 v1 pith:XPYETL4Z submitted 2019-02-24 cs.LG stat.ML

Wei Peng , Yuhong Dai , Hui Zhang , Lizhi Cheng This is my paper · ORCID
classification cs.LGstat.ML
keywords accelerationcentripetalbehaviorscyclicgansmethodtrainingadversarial
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Layer-wise Quantization for Quantized Optimistic Dual Averaging

    cs.LG 2025-05 reject novelty 7.0 of 10

    A new quantized optimistic dual averaging algorithm with layer-wise adaptive compression is presented, with theoretical convergence guarantees for monotone variational inequalities and empirical speedups on distribute...

  2. On the convergence of single-call stochastic extra-gradient methods

    math.OC 2019-08 accept novelty 7.0 of 10

    Single-call stochastic extra-gradient methods achieve O(1/t) ergodic convergence in deterministic monotone variational inequalities and O(1/t) last-iterate local convergence around regular solutions in stochastic non-...

  3. Convergence of Gradient Methods on Bilinear Zero-Sum Games

    cs.LG 2019-08 conditional novelty 7.0 of 10

    For bilinear zero-sum games, the paper derives necessary and sufficient convergence conditions and optimal linear rates for generalized GD, EG, OGD, and momentum methods, with Gauss-Seidel updates converging in a larg...

Pith tools