Error Feedback Can Accurately Compress Preconditioners

• URL: http://arxiv.org/abs/2306.06098v5
• Date: Wed, 5 Jun 2024 15:45:58 GMT
• Title: Error Feedback Can Accurately Compress Preconditioners
• Authors: Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic, Elias Frantar, Dan Alistarh,
• Abstract summary: Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of currents for deep learning. Yet, existing approaches for accurate full-matrix preconditioning, such as Full-Matrix Adagrad (GGT) or Matrix-Free Approximate Curvature (M-FAC) suffer from massive storage costs when applied even to small-scale models. In this paper, we address this issue via a novel and efficient error-feedback technique that can be applied to compress preconditioners by up to two orders of magnitude in practice, without loss of convergence.
• Score: 43.60787513716217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix preconditioning, such as Full-Matrix Adagrad (GGT) or Matrix-Free Approximate Curvature (M-FAC) suffer from massive storage costs when applied even to small-scale models, as they must store a sliding window of gradients, whose memory requirements are multiplicative in the model dimension. In this paper, we address this issue via a novel and efficient error-feedback technique that can be applied to compress preconditioners by up to two orders of magnitude in practice, without loss of convergence. Specifically, our approach compresses the gradient information via sparsification or low-rank compression \emph{before} it is fed into the preconditioner, feeding the compression error back into future iterations. Experiments on deep neural networks show that this approach can compress full-matrix preconditioners to up to 99\% sparsity without accuracy loss, effectively removing the memory overhead of full-matrix preconditioners such as GGT and M-FAC. Our code is available at \url{https://github.com/IST-DASLab/EFCP}.

Related papers

• 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)
• Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy [5.699098817569033]
  This paper introduces an activation-aware model compression methodology that uses selective low-rank weight tensor approximations of different layers to reduce the parameter count of ViTs. The presented method significantly reduces the parameter count of DeiT-B by 60% with less than 1% accuracy drop on the ImageNet dataset. In addition to this, the presented compression technique can compress large DeiT/ViT models to have about the same model size as smaller DeiT/ViT variants while yielding up to 1.8% accuracy gain.
  arXiv  Detail & Related papers  (2024-02-08T19:01:14Z)
• Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth [83.15263499262824]
  We prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. We show how to improve upon Gaussian performance for the compression of sparse data by adding a denoising function to a shallow architecture. We validate our findings on image datasets, such as CIFAR-10 and MNIST.
  arXiv  Detail & Related papers  (2024-02-07T16:32:29Z)
• Curvature-Informed SGD via General Purpose Lie-Group Preconditioners [6.760212042305871]
  We present a novel approach to accelerate gradient descent (SGD) by utilizing curvature information. Our approach involves two preconditioners: a matrix-free preconditioner and a low-rank approximation preconditioner. We demonstrate that Preconditioned SGD (PSGD) outperforms SoTA on Vision, NLP, and RL tasks.
  arXiv  Detail & Related papers  (2024-02-07T03:18:00Z)
• Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [41.299675080384]
  Mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression.
  arXiv  Detail & Related papers  (2024-01-03T05:26:57Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression [8.080129426746288]
  Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory. We propose a memory-efficient CNN training framework (called COMET) that leverages error-bounded lossy compression. Our framework can significantly reduce the training memory consumption by up to 13.5X over the baseline training and 1.8X over another state-of-the-art compression-based framework.
  arXiv  Detail & Related papers  (2021-11-18T07:43:45Z)
• Large Scale Private Learning via Low-rank Reparametrization [77.38947817228656]
  We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks. We are the first able to apply differential privacy on the BERT model and achieve an average accuracy of $83.9%$ on four downstream tasks.
  arXiv  Detail & Related papers  (2021-06-17T10:14:43Z)
• A Generic Network Compression Framework for Sequential Recommender Systems [71.81962915192022]
  Sequential recommender systems (SRS) have become the key technology in capturing user's dynamic interests and generating high-quality recommendations. We propose a compressed sequential recommendation framework, termed as CpRec, where two generic model shrinking techniques are employed. By the extensive ablation studies, we demonstrate that the proposed CpRec can achieve up to 4$sim$8 times compression rates in real-world SRS datasets.
  arXiv  Detail & Related papers  (2020-04-21T08:40:55Z)

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.