# Decentralized projected Riemannian stochastic recursive momentum method for nonconvex optimization

arXiv: https://arxiv.org/abs/2412.02382 · HTML: https://mlsanity.com/paper/2412.02382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2024.

## Built on by (most cited first, 1 of 1)

- [Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance](https://mlsanity.com/paper/2602.11789/) (2026)

## Abstract (arXiv)

This paper studies decentralized optimization over a compact submanifold within a communication network of n nodes, where each node possesses a smooth non-convex local cost function, and the goal is to jointly minimize the sum of these local costs. We focus particularly on the online setting, where local data is processed in real-time as it streams in, without the need for full data storage. We propose a decentralized projected Riemannian stochastic recursive momentum (DPRSRM) method that employs local hybrid stochastic gradient estimators and uses the network to track the global gradient. DPRSRM achieves an oracle complexity of (O(ε^-frac32)), outperforming existing methods that have at most (O(ε-2)) complexity. Our method requires only O(1) gradient evaluations per iteration for each local node and does not require restarting with a large batch gradient. Furthermore, we demonstrate the effectiveness of our proposed methods compared to state-of-the-art ones through numerical experiments on principal component analysis problems and low-rank matrix completion.