mlsanityData to 7 Oct 2026

The convergence of the Stochastic Gradient Descent (SGD) : a self-contained proof

arXiv 2103.14350 ↗First posted 26 Mar 2021stat.ML cs.LG math.PRcited by 9

Not on the map. Why?

Abstract (arXiv)

We give here a proof of the convergence of the Stochastic Gradient Descent (SGD) in a self-contained manner.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 4 of its 5 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

4 of 5 references.

References · 4

  1. 2020Stochastic Runge-Kutta methods and adaptive SGD-G2 stochastic gradient descentcited by 4
  2. 2019Radon Sobolev Variational Auto-Encoderscited by 2
  3. 2019Stochastic learning control of inhomogeneous quantum ensemblescited by 1
  4. 2020Convergence dynamics of Generative Adversarial Networks: the dual metric flowscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 3; 2024: 2; 2025: 1.

9 papers.

  1. 2021A Bregman Learning Framework for Sparse Neural Networkscited by 15
  2. 2024Optimal time sampling in physics-informed neural networkscited by 3
  3. 2024Convergence of a L2 regularized Policy Gradient Algorithm for the Multi Armed Banditcited by 2
  4. 2022Analysis of Kinetic Models for Label Switching and Stochastic Gradient Descentcited by 0
  5. 2022Prediction intervals for neural network models using weighted asymmetric loss functionscited by 0
  6. 2023A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysiscited by 0
  7. 2023Learning Continually on a Sequence of Graphs -- The Dynamical System Waycited by 0
  8. 2023Onflow: a model free, online portfolio allocation algorithm robust to transaction feescited by 0
  9. 2025Probabilistic and nonlinear compressive sensingcited by 0