PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training

• URL: http://arxiv.org/abs/2602.23111v1
• Date: Thu, 26 Feb 2026 15:23:34 GMT
• Title: PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
• Authors: Yanyi Li, Yimu Zhang, Cong Fang,
• Abstract summary: We propose Principal-Random Subspace for LLM Activation Compression (PRAC)<n>PRAC decomposes activations into two components: a principal subspace captured via SVD to retain dominant information, and a random subspace sampled from the orthogonal complement to approximate the tail.<n>Experiments on pre-training and fine-tuning tasks demonstrate that PRAC achieves up to 36% total memory reduction with negligible performance degradation and minimal computational cost.
• Score: 5.275001711555517
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activations have become the primary memory bottleneck in large-batch LLM training. However, existing compression methods fail to exploit the spectral structure of activations, resulting in slow convergence or limited compression. To address this, we bridge the relationship between the algorithm's fast convergence and the requirements for subspace projection, and show that an effective compression should yield an unbiased estimate of the original activation with low variance. We propose Principal-Random Subspace for LLM Activation Compression (PRAC), which novelly decomposes activations into two components: a principal subspace captured via SVD to retain dominant information, and a random subspace sampled from the orthogonal complement to approximate the tail. By introducing a precise scaling factor, we prove that PRAC yields an unbiased gradient estimator with minimum variance under certain conditions. Extensive experiments on pre-training and fine-tuning tasks demonstrate that PRAC achieves up to 36% total memory reduction with negligible performance degradation and minimal computational cost.

Related papers

• Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog [72.4168434368873]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources.<n>We propose a gradual compacting method that divides the compression process into multiple fine-grained iterations.<n>This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss.
  arXiv  Detail & Related papers  (2026-02-04T06:56:52Z)
• LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning [9.009523608709117]
  On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments.<n>Existing activation compression methods reduce this cost but rely on repeated low-rank decompositions, introducing computational overhead.<n>We propose LANCE, a framework that performs one-shot higher-order Singular Value Decompsoition (SVD) to obtain a reusable low-rank subspace for activation projection.
  arXiv  Detail & Related papers  (2025-09-25T21:33:40Z)
• FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression [15.784158079414235]
  FLAT-LLM is a training-free structural compression method based on fine-grained low-rank transformations in the activation space.<n>It achieves efficient and effective weight compression without recovery fine-tuning, which could complete the calibration within a few minutes.
  arXiv  Detail & Related papers  (2025-05-29T19:42:35Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• Optimizing Singular Spectrum for Large Language Model Compression [95.7621116637755]
  We introduce SoCo, a novel compression framework that learns to rescale the decomposed components of SVD in a data-driven manner.<n>Thanks to the learnable singular spectrum, SoCo adaptively prunes components according to the sparsified importance scores.<n> Experimental evaluations across multiple LLMs and benchmarks demonstrate that SoCo surpasses the state-of-the-art methods in model compression.
  arXiv  Detail & Related papers  (2025-02-20T23:18:39Z)
• TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs [58.19080159470868]
  We propose a novel low-rank ZO estimator, TeZO, which captures the low-rankness across both the model and temporal dimension.<n>Specifically, we represent ZO perturbations along the temporal dimension as a 3D tensor and employ Canonical Polyadic Decomposition (CPD) to extract each low-rank 2D matrix.
  arXiv  Detail & Related papers  (2025-01-31T11:34:03Z)
• EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [84.70637613266835]
  EoRA is a fine-tuning-free method that augments compressed Large Language Models with low-rank matrices.<n>EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs [28.70239743254508]
  We present the first structural binarization method for LLM compression to less than 1-bit precision. We observe that some weights in binarized LLMs can be randomly flipped without significant performance degradation. Our approach performs better than other compressed binarization methods while significantly reducing memory requirements.
  arXiv  Detail & Related papers  (2024-08-03T15:07:44Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.