Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization

• URL: http://arxiv.org/abs/2408.00923v1
• Date: Thu, 1 Aug 2024 21:27:31 GMT
• Title: Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
• Authors: Róisín Luo, Alexandru Drimbarean, James McDermott, Colm O'Riordan,
• Abstract summary: This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, by framing optimal quantization as an architecture search problem within convolutional neural networks (ConvNets) Our framework, dubbed textbfCoRa, searches for the optimal architectures of low-rank adapters. textbfCoRa achieves comparable performance against both state-of-the-art quantization-aware training and post-training quantization baselines.
• Score: 41.94295877935867
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks (ConvNets). Our framework, dubbed \textbf{CoRa} (Optimal Quantization Residual \textbf{Co}nvolutional Operator Low-\textbf{Ra}nk Adaptation), is motivated by two key aspects. Firstly, quantization residual knowledge, i.e. the lost information between floating-point weights and quantized weights, has long been neglected by the research community. Reclaiming the critical residual knowledge, with an infinitesimal extra parameter cost, can reverse performance degradation without training. Secondly, state-of-the-art quantization frameworks search for optimal quantized weights to address the performance degradation. Yet, the vast search spaces in weight optimization pose a challenge for the efficient optimization in large models. For example, state-of-the-art BRECQ necessitates $2 \times 10^4$ iterations to quantize models. Fundamentally differing from existing methods, \textbf{CoRa} searches for the optimal architectures of low-rank adapters, reclaiming critical quantization residual knowledge, within the search spaces smaller compared to the weight spaces, by many orders of magnitude. The low-rank adapters approximate the quantization residual weights, discarded in previous methods. We evaluate our approach over multiple pre-trained ConvNets on ImageNet. \textbf{CoRa} achieves comparable performance against both state-of-the-art quantization-aware training and post-training quantization baselines, in $4$-bit and $3$-bit quantization, by using less than $250$ iterations on a small calibration set with $1600$ images. Thus, \textbf{CoRa} establishes a new state-of-the-art in terms of the optimization efficiency in low-bit quantization.

Related papers

• 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)
• BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation [116.26521375592759]
  Quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation. Extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures results in severe performance degeneration. This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration.
  arXiv  Detail & Related papers  (2022-07-04T13:25:49Z)
• Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks [1.398698203665363]
  In this paper, we explore non-linear quantization techniques for exploiting lower bit precision. We developed the Quantization Aware Training (QAT) algorithm that allowed training of low bit width Power-of-Two (PoT) networks. At the same time, PoT quantization vastly reduces the computational complexity of the neural network.
  arXiv  Detail & Related papers  (2022-03-09T19:57:14Z)
• Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment [15.720551497037176]
  We propose an auto-tuner known as Quantune to accelerate the search for the configurations of quantization. We show that Quantune reduces the search time for quantization by approximately 36.5x with an accuracy loss of 0.07 0.65% across six CNN models.
  arXiv  Detail & Related papers  (2022-02-10T14:05:02Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Quantized Proximal Averaging Network for Analysis Sparse Coding [23.080395291046408]
  We unfold an iterative algorithm into a trainable network that facilitates learning sparsity prior to quantization. We demonstrate applications to compressed image recovery and magnetic resonance image reconstruction.
  arXiv  Detail & Related papers  (2021-05-13T12:05:35Z)
• Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks [73.29587731448345]
  This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. Second, to obtain low bit-width activations, existing works consider all channels equally.
  arXiv  Detail & Related papers  (2020-12-26T15:21:18Z)
• Recurrence of Optimum for Training Weight and Activation Quantized Networks [4.103701929881022]
  Training deep learning models with low-precision weights and activations involves a demanding optimization task. We show how to overcome the nature of network quantization. We also show numerical evidence of the recurrence phenomenon of weight evolution in training quantized deep networks.
  arXiv  Detail & Related papers  (2020-12-10T09:14:43Z)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)
• Gradient $\ell_1$ Regularization for Quantization Robustness [70.39776106458858]
  We derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our approach enables storing a single set of weights that can be quantized on-demand to different bit-widths.
  arXiv  Detail & Related papers  (2020-02-18T12:31:34Z)

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.