On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Abstract

Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which matches the mainstream practical heuristics. We show the convergence to a global solution of shuffling SGD for a class of non-convex functions under over-parameterized settings. Our analysis employs more relaxed non-convex assumptions than previous literature. Nevertheless, we maintain the desired computational complexity as shuffling SGD has achieved in the general convex setting.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Nguyen and Tran. "On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms." Neural Information Processing Systems, 2023.

Markdown

[Nguyen and Tran. "On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/nguyen2023neurips-convergence/)

BibTeX

@inproceedings{nguyen2023neurips-convergence,
  title     = {{On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms}},
  author    = {Nguyen, Lam and Tran, Trang H.},
  booktitle = {Neural Information Processing Systems},
  year      = {2023},
  url       = {https://mlanthology.org/neurips/2023/nguyen2023neurips-convergence/}
}