Pith. sign in

REVIEW 2 cited by

Adam with model exponential moving average is effective for nonconvex optimization

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 2405.18199 v2 pith:EI5WFVAH submitted 2024-05-28 cs.LG math.OC

Adam with model exponential moving average is effective for nonconvex optimization

classification cs.LG math.OC
keywords adammodeloptimizationanalysisaveragedemonstrateexponentialmoving
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work, we offer a theoretical analysis of two modern optimization techniques for training large and complex models: (i) adaptive optimization algorithms, such as Adam, and (ii) the model exponential moving average (EMA). Specifically, we demonstrate that a clipped version of Adam with model EMA achieves the optimal convergence rates in various nonconvex optimization settings, both smooth and nonsmooth. Moreover, when the scale varies significantly across different coordinates, we demonstrate that the coordinate-wise adaptivity of Adam is provably advantageous. Notably, unlike previous analyses of Adam, our analysis crucially relies on its core elements -- momentum and discounting factors -- as well as model EMA, motivating their wide applications in practice.

discussion (0)

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

Forward citations

Cited by 2 Pith papers

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

  1. Differentially Private Natural Gradient Descent

    cs.LG 2026-07 conditional novelty 6.0

    DP-NGD enables second-order optimization under differential privacy by decoupling curvature estimation onto public data, performing isotropic DP operations in a whitened space, and dynamically clamping curvature eigen...

  2. Central limit theorem for the averaged Adam optimizer

    math.PR 2026-06 unverdicted novelty 5.0

    Establishes a central limit theorem for averaged Adam with n^{-1/2} convergence rate to an attracting zero and covariance determined by the algorithm at the attractor.