Addition is almost all you need: Compressing neural networks with double binary factorization

• URL: http://arxiv.org/abs/2505.11076v2
• Date: Tue, 17 Jun 2025 16:42:33 GMT
• Title: Addition is almost all you need: Compressing neural networks with double binary factorization
• Authors: Vladimír Boža, Vladimír Macko,
• Abstract summary: Double Binary Factorization (DBF) is a novel method that factorizes dense weight matrices into products of two binary (sign) matrices, each accompanied by scaling vectors.<n>DBF preserves the efficiency advantages of binary representations while achieving compression rates that are competitive with or superior to state-of-the-art methods.<n>In a 2-bit per weight range, DBF is competitive with the best quantization methods like QuIP# and QTIP.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Binary quantization approaches, which replace weight matrices with binary matrices and substitute costly multiplications with cheaper additions, offer a computationally efficient approach to address the increasing computational and storage requirements of Large Language Models (LLMs). However, the severe quantization constraint ($\pm1$) can lead to significant accuracy degradation. In this paper, we propose Double Binary Factorization (DBF), a novel method that factorizes dense weight matrices into products of two binary (sign) matrices, each accompanied by scaling vectors. DBF preserves the efficiency advantages of binary representations while achieving compression rates that are competitive with or superior to state-of-the-art methods. Specifically, in a 1-bit per weight range, DBF is better than existing binarization approaches. In a 2-bit per weight range, DBF is competitive with the best quantization methods like QuIP\# and QTIP. Unlike most existing compression techniques, which offer limited compression level choices, DBF allows fine-grained control over compression ratios by adjusting the factorization's intermediate dimension. Based on this advantage, we further introduce an algorithm for estimating non-uniform layer-wise compression ratios for DBF, based on previously developed channel pruning criteria. Code available at: https://github.com/usamec/double_binary

Related papers

• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook [20.89001326838199]
  We present BTC-LLM, a novel sub-1-bit large language model (LLM) quantization framework.<n>Our approach incorporates two key innovations: (1) a Learnable Transformation that optimize invertible scaling and rotation to align binarized weights with full-precision distributions, and (2) a Flash and Accurate Binary Codebook that identifies recurring binary vector clusters.
  arXiv  Detail & Related papers  (2025-05-24T03:57:19Z)
• BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution [63.777210548110425]
  We propose BiMaCoSR, which combines binarization and one-step distillation to obtain extreme compression and acceleration.<n>BiMaCoSR achieves a 23.8x compression ratio and a 27.4x speedup ratio compared to FP counterpart.
  arXiv  Detail & Related papers  (2025-02-01T06:34:55Z)
• Quantization-aware Matrix Factorization for Low Bit Rate Image Compression [8.009813033356478]
  Lossy image compression is essential for efficient transmission and storage.<n>We introduce a quantization-aware matrix factorization (QMF) to develop a novel lossy image compression method.<n>Our method consistently outperforms JPEG at low bit rates below 0.25 bits per pixel (bpp) and remains comparable at higher bit rates.
  arXiv  Detail & Related papers  (2024-08-22T19:08:08Z)
• DB-LLM: Accurate Dual-Binarization for Efficient LLMs [83.70686728471547]
  Large language models (LLMs) have significantly advanced the field of natural language processing. Existing ultra-low-bit quantization always causes severe accuracy drops. We propose a novel Dual-Binarization method for LLMs, namely DB-LLM.
  arXiv  Detail & Related papers  (2024-02-19T09:04:30Z)
• Neural Network Compression using Binarization and Few Full-Precision Weights [7.206962876422061]
  Automatic Prune Binarization (APB) is a novel compression technique combining quantization with pruning. APB enhances the representational capability of binary networks using a few full-precision weights. APB delivers better accuracy/memory trade-off compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-15T08:52:00Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Monarch: Expressive Structured Matrices for Efficient and Accurate Training [64.6871423399431]
  Large neural networks excel in many domains, but they are expensive to train and fine-tune. A popular approach to reduce their compute or memory requirements is to replace dense weight matrices with structured ones. We propose a class of matrices (Monarch) that is hardware-efficient.
  arXiv  Detail & Related papers  (2022-04-01T17:37:29Z)
• Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations [0.0]
  Quantization based model compression serves as high performing and fast approach for inference. Models that constrain the weights to binary values enable efficient implementation of the ubiquitous dot product.
  arXiv  Detail & Related papers  (2021-07-03T10:29:34Z)
• Binary Matrix Factorisation and Completion via Integer Programming [3.4376560669160394]
  We present a compact and two exponential size integer programs (IPs) for the rank-k binary matrix factorisation problem (k-BMF) We show that the compact IP has a weak LP relaxation, while the exponential size LPs have a stronger equivalent LP relaxation.
  arXiv  Detail & Related papers  (2021-06-25T05:17:51Z)
• BinaryBERT: Pushing the Limit of BERT Quantization [74.65543496761553]
  We propose BinaryBERT, which pushes BERT quantization to the limit with weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscapes. Empirical results show that BinaryBERT has negligible performance drop compared to the full-precision BERT-base.
  arXiv  Detail & Related papers  (2020-12-31T16:34:54Z)
• Linear Convergent Decentralized Optimization with Compression [50.44269451541387]
  Existing decentralized algorithms with compression mainly focus on compressing DGD-type algorithms. Motivated by primal-dual algorithms, this paper proposes first underlineLinunderlineEAr convergent. underlineDecentralized with compression, LEAD.
  arXiv  Detail & Related papers  (2020-07-01T04:35:00Z)

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.