Pith. sign in

REVIEW 4 cited by

Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations

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 1811.01558 v1 pith:JAN5S2J6 submitted 2018-11-05 cs.LG stat.ML

Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations

classification cs.LG stat.ML
keywords stochasticgradientalgorithmsequationsapproximationdynamicsfoundationsmathematical
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We develop the mathematical foundations of the stochastic modified equations (SME) framework for analyzing the dynamics of stochastic gradient algorithms, where the latter is approximated by a class of stochastic differential equations with small noise parameters. We prove that this approximation can be understood mathematically as an weak approximation, which leads to a number of precise and useful results on the approximations of stochastic gradient descent (SGD), momentum SGD and stochastic Nesterov's accelerated gradient method in the general setting of stochastic objectives. We also demonstrate through explicit calculations that this continuous-time approach can uncover important analytical insights into the stochastic gradient algorithms under consideration that may not be easy to obtain in a purely discrete-time setting.

discussion (0)

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

Forward citations

Cited by 4 Pith papers

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

  1. Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate

    math.OC 2026-04 unverdicted novelty 8.0

    Adam-HNAG is a splitting-based reformulation of Adam that yields the first convergence proof for Adam-type methods, including accelerated rates, in convex smooth optimization.

  2. Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent

    math.OC 2026-06 unverdicted novelty 7.0

    Derives ODE deterministic equivalents and an adversarial homogenized SDE for SGD iterates in high-dim ℓ2-adversarial training, showing no constant learning rate ensures monotone descent for single-class adversarial le...

  3. Thermodynamic Irreversibility of Training Algorithms

    cond-mat.stat-mech 2026-05 unverdicted novelty 6.0

    Four characterizations of irreversibility in training algorithms are equivalent to leading order in step size and produce an emergent force that breaks reparametrization symmetries while favoring minimum entropy produ...

  4. Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks

    stat.ML 2025-11 unverdicted novelty 5.0

    At the critical step-size scaling for SGD in high-dimensional single-layer networks, effective dynamics gain a diffusive correction term that changes the phase diagram and reduces to an Ornstein-Uhlenbeck process near...