Pith. sign in

REVIEW 1 cited by

NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer

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 2209.14937 v2 pith:6CKBJDZO submitted 2022-09-29 math.OC cs.LGcs.NAmath.NA

classification math.OCcs.LGcs.NAmath.NA
keywords stochasticacceleratedlearningmodelsnag-gsanalysisclassicalconvergence
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic gradient flow. In this paper we propose a novel, robust and accelerated stochastic optimizer that relies on two key elements: (1) an accelerated Nesterov-like Stochastic Differential Equation (SDE) and (2) its semi-implicit Gauss-Seidel type discretization. The convergence and stability of the obtained method, referred to as NAG-GS, are first studied extensively in the case of the minimization of a quadratic function. This analysis allows us to come up with an optimal learning rate in terms of the convergence rate while ensuring the stability of NAG-GS. This is achieved by the careful analysis of the spectral radius of the iteration matrix and the covariance matrix at stationarity with respect to all hyperparameters of our method. Further, we show that NAG- GS is competitive with state-of-the-art methods such as momentum SGD with weight decay and AdamW for the training of machine learning models such as the logistic regression model, the residual networks models on standard computer vision datasets, Transformers in the frame of the GLUE benchmark and the recent Vision Transformers.

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. Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models

    cs.LG 2025-08 conditional novelty 6.0 of 10

    AdaGram applies a dynamical low-rank integrator to the preconditioner of adaptive gradient methods, achieving full-matrix-like updates with rank 1-5 approximations at low cost on small GLM benchmarks.

Pith tools