PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off

• URL: http://arxiv.org/abs/2312.01581v2
• Date: Tue, 06 May 2025 03:32:16 GMT
• Title: PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off
• Authors: Sachit Kuhar, Yash Jain, Alexey Tumanov,
• Abstract summary: Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.<n>This paper introduces the concept of repetition-sparsity trade-off that helps explain computational efficiency during inference.<n>We propose PLUM, a unified co-design framework that integrates inference systems and quantization to leverage the repetition-sparsity trade-off.
• Score: 2.326200609038491
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface. This paper introduces the concept of repetition-sparsity trade-off that helps explain computational efficiency during inference. We propose PLUM, a unified co-design framework that integrates DNN inference systems and quantization (forward and backward pass) to leverage the repetition-sparsity trade-off to improve inference efficiency. Our results demonstrate that PLUM's quantization method is more accurate than binary quantization with the same number of non-zero weights. Detailed analysis indicates that signed binarization generates a smaller distribution of effectual (non-zero) parameters nested within a larger distribution of total parameters of latent full-precision weights for a DNN block. Finally, the proposed PLUM framework achieves a 26% speedup on real hardware, doubles energy efficiency, and reduces density by 2.8x compared to binary methods while retaining top-1 accuracy when compared to prior-art methods for ResNets on ImageNet (by achieving 66.2% top-1 accuracy), presenting an alternative solution for deploying efficient models in resource-limited environments.

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)
• Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting [13.270381125055275]
  We propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight. We develop an improved KL metric to determine optimal quantization scales for activation. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss.
  arXiv  Detail & Related papers  (2023-12-17T02:31:20Z)
• 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)
• BiBench: Benchmarking and Analyzing Network Binarization [72.59760752906757]
  Network binarization emerges as one of the most promising compression approaches offering extraordinary computation and memory savings. Common challenges of binarization, such as accuracy degradation and efficiency limitation, suggest that its attributes are not fully understood. We present BiBench, a rigorously designed benchmark with in-depth analysis for network binarization.
  arXiv  Detail & Related papers  (2023-01-26T17:17:16Z)
• Signed Binary Weight Networks [17.07866119979333]
  Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. We propose a new method called signed-binary networks to improve efficiency further. Our method achieves comparable accuracy on ImageNet and CIFAR10 datasets with binary and can lead to 69% sparsity.
  arXiv  Detail & Related papers  (2022-11-25T00:19:21Z)
• BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance [54.214426436283134]
  Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. We present a strong yet efficient binary neural network for KWS, namely BiFSMNv2, pushing it to the real-network accuracy performance. We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1x speedup and 20.2x storage-saving on edge hardware.
  arXiv  Detail & Related papers  (2022-11-13T18:31:45Z)
• AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets [27.022212653067367]
  This paper studies the Binary Neural Networks (BNNs) in which weights and activations are both binarized into 1-bit values. We present a simple yet effective approach called AdaBin to adaptively obtain the optimal binary sets. Experimental results on benchmark models and datasets demonstrate that the proposed AdaBin is able to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-17T05:43:33Z)
• Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design [68.86220939532373]
  The finite precision level is captured through the use of quantized neural networks (QNNs) that quantize weights and activations in fixed-precision format. The proposed FL framework can reduce energy consumption until convergence by up to 70% compared to a baseline FL algorithm.
  arXiv  Detail & Related papers  (2022-07-19T16:37:24Z)
• Low-bit Shift Network for End-to-End Spoken Language Understanding [7.851607739211987]
  We propose the use of power-of-two quantization, which quantizes continuous parameters into low-bit power-of-two values. This reduces computational complexity by removing expensive multiplication operations and with the use of low-bit weights.
  arXiv  Detail & Related papers  (2022-07-15T14:34:22Z)
• Bimodal Distributed Binarized Neural Networks [3.0778860202909657]
  Binarization techniques, however, suffer from ineligible performance degradation compared to their full-precision counterparts. We propose a Bi-Modal Distributed binarization method (methodname) That imposes bi-modal distribution of the network weights by kurtosis regularization.
  arXiv  Detail & Related papers  (2022-04-05T06:07:05Z)
• BiFSMN: Binary Neural Network for Keyword Spotting [47.46397208920726]
  BiFSMN is an accurate and extreme-efficient binary neural network for KWS. We show that BiFSMN can achieve an impressive 22.3x speedup and 15.5x storage-saving on real-world edge hardware.
  arXiv  Detail & Related papers  (2022-02-14T05:16:53Z)
• Distribution-sensitive Information Retention for Accurate Binary Neural Network [49.971345958676196]
  We present a novel Distribution-sensitive Information Retention Network (DIR-Net) to retain the information of the forward activations and backward gradients. Our DIR-Net consistently outperforms the SOTA binarization approaches under mainstream and compact architectures. We conduct our DIR-Net on real-world resource-limited devices which achieves 11.1 times storage saving and 5.4 times speedup.
  arXiv  Detail & Related papers  (2021-09-25T10:59:39Z)
• 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)
• Fully Quantized Image Super-Resolution Networks [81.75002888152159]
  We propose a Fully Quantized image Super-Resolution framework (FQSR) to jointly optimize efficiency and accuracy. We apply our quantization scheme on multiple mainstream super-resolution architectures, including SRResNet, SRGAN and EDSR. Our FQSR using low bits quantization can achieve on par performance compared with the full-precision counterparts on five benchmark datasets.
  arXiv  Detail & Related papers  (2020-11-29T03:53:49Z)
• BiPointNet: Binary Neural Network for Point Clouds [73.07852523426224]
  BiPointNet is the first model binarization approach for efficient deep learning on point clouds. We show that BiPointNet gives an impressive 14.7x speedup and 18.9x storage saving on real-world resource-constrained devices.
  arXiv  Detail & Related papers  (2020-10-12T07:54:51Z)
• High-Capacity Expert Binary Networks [56.87581500474093]
  Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an unsolved challenging research problem. We propose Expert Binary Convolution, which, for the first time, tailors conditional computing to binary networks by learning to select one data-specific expert binary filter at a time conditioned on input features.
  arXiv  Detail & Related papers  (2020-10-07T17:58:10Z)
• QuantNet: Learning to Quantize by Learning within Fully Differentiable Framework [32.465949985191635]
  This paper proposes a meta-based quantizer named QuantNet, which utilizes a differentiable sub-network to directly binarize the full-precision weights. Our method not only solves the problem of gradient mismatching, but also reduces the impact of discretization errors, caused by the binarizing operation in the deployment.
  arXiv  Detail & Related papers  (2020-09-10T01:41:05Z)
• WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic [57.07483440807549]
  We propose a method that adapts neural networks to use low-resolution (8-bit) additions in the accumulators, achieving classification accuracy comparable to their 32-bit counterparts. We demonstrate the efficacy of our approach on both software and hardware platforms.
  arXiv  Detail & Related papers  (2020-07-26T23:18:38Z)

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.