No official code found. Best implementation: pqyang9/Adaptive-SGD (1 star, MIT, last commit 2025-03-28).
We prove a convergence theorem for stochastic gradient descents on manifolds with adaptive learning rate and apply it to the weighted low-rank approximation problem.
Mirror Descent on Riemannian Manifolds
Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses
Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds
Stochastic Modified Flows for Riemannian Stochastic Gradient Descent
Convergence rates of stochastic gradient method with independent sequences of step-size and momentum weight
Tame Riemannian Stochastic Approximation
@article{yang2025adaptive,
title = {Adaptive Stochastic Gradient Descents on Manifolds with an Application on Weighted Low-Rank Approximation},
author = {Peiqi Yang and Conglong Xu and Hao Wu},
year = {2025},
eprint = {2503.11833},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2503.11833v2}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2503.11833)