# A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models

arXiv: https://arxiv.org/abs/2502.07222 · HTML: https://mlsanity.com/paper/2502.07222/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2025.

## Built on by (most cited first, 16 of 16)

- [FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed](https://mlsanity.com/paper/2506.09034/) (2025)
- [Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization](https://mlsanity.com/paper/2602.17155/) (2026)
- [Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees](https://mlsanity.com/paper/2507.08784/) (2025)
- [On the Convergence Rate of LoRA Gradient Descent](https://mlsanity.com/paper/2512.18248/) (2025)
- [AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections](https://mlsanity.com/paper/2505.12455/) (2025)
- [CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure](https://mlsanity.com/paper/2509.18993/) (2025)
- [An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2509.05213/) (2025)
- [MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling](https://mlsanity.com/paper/2511.00056/) (2025)
- [BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models](https://mlsanity.com/paper/2512.12131/) (2025)
- [FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2602.03019/) (2026)
- [AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments](https://mlsanity.com/paper/2605.00650/) (2026)
- [Geometrically Principled Randomized Optimization for Efficient LLM Training](https://mlsanity.com/paper/2510.01878/) (2025)
- [Convergence Analysis of Randomized Subspace Normalized SGD under Heavy-Tailed Noise](https://mlsanity.com/paper/2601.20399/) (2026)
- [PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training](https://mlsanity.com/paper/2602.23111/) (2026)
- [BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization](https://mlsanity.com/paper/2605.10288/) (2026)
- [Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon](https://mlsanity.com/paper/2610.19844/) (2026)

## Abstract (arXiv)

The memory challenges associated with training Large Language Models (LLMs) have become a critical concern, particularly when using the Adam optimizer. To address this issue, numerous memory-efficient techniques have been proposed, with GaLore standing out as a notable example designed to reduce the memory footprint of optimizer states. However, these approaches do not alleviate the memory burden imposed by activations, rendering them unsuitable for scenarios involving long context sequences or large mini-batches. Moreover, their convergence properties are still not well-understood in the literature. In this work, we introduce a Randomized Subspace Optimization framework for pre-training and fine-tuning LLMs. Our approach decomposes the high-dimensional training problem into a series of lower-dimensional subproblems. At each iteration, a random subspace is selected, and the parameters within that subspace are optimized. This structured reduction in dimensionality allows our method to simultaneously reduce memory usage for both activations and optimizer states. We establish comprehensive convergence guarantees and derive rates for various scenarios, accommodating different optimization strategies to solve the subproblems. Extensive experiments validate the superior memory and communication efficiency of our method, achieving performance comparable to GaLore and Adam.