Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch

• URL: http://arxiv.org/abs/2510.16088v1
• Date: Sat, 18 Oct 2025 13:58:59 GMT
• Title: Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch
• Authors: Zia Badar,
• Abstract summary: Quantization of neural networks provides benefits of inference in less compute and memory requirements.<n>Previous work in quantization used a non-differentiable approach and for learning.<n>We provide proof of convergence of our approach to the optimal neural network.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a non-differentiable approach and for learning; the derivative is usually set manually in backpropogation which make the learning ability of algorithm questionable, our approach is not just differentiable, we also provide proof of convergence of our approach to the optimal neural network. Second previous work in shift/logrithmic quantization either have avoided activation quantization along with weight quantization or achieved less accuracy. Learning logrithmic quantize values of form $2^n$ requires the quantization function can scale to more than 1 bit quantization which is another benifit of our quantization that it provides $n$ bits quantization as well. Our approach when tested with image classification task using imagenet dataset, resnet18 and weight quantization only achieves less than 1 percent accuracy compared to full precision accuracy while taking only 15 epochs to train using shift bit quantization and achieves comparable to SOTA approaches accuracy in both weight and activation quantization using shift bit quantization in 15 training epochs with slightly higher(only higher cpu instructions) inference cost compared to 1 bit quantization(without logrithmic quantization) and not requiring any higher precision multiplication.

Related papers

• ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization [73.60493264901359]
  We present a unified framework for rigorous comparisons across 1-bit, 1.58-bit, 2-bit, 3-bit, and 4-bit quantization settings.<n>We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off.<n>Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• Supervised binary classification of small-scale digit images and weighted graphs with a trapped-ion quantum processor [56.089799129458875]
  We present the results of benchmarking a quantum processor based on trapped $171$Yb$+$ ions.<n>We perform a supervised binary classification on two types of datasets: small binary digit images and weighted graphs with a ring topology.
  arXiv  Detail & Related papers  (2024-06-17T18:20:51Z)
• Attention Round for Post-Training Quantization [0.9558392439655015]
  This paper presents a novel quantification method called Attention Round. The probability of being mapped to different quantified values is negatively correlated with the distance between the quantified values and w, and decay with a Gaussian function. For ResNet18 and MobileNetV2, the post-training quantization proposed in this paper only require 1,024 training data and 10 minutes to complete the quantization process.
  arXiv  Detail & Related papers  (2022-07-07T05:04:21Z)
• PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization [12.136898590792754]
  We analyze the problems of quantization on vision transformers. We propose the twin uniform quantization method to reduce the quantization error on these activation values. Experiments show the quantized vision transformers achieve near-lossless prediction accuracy (less than 0.5% drop at 8-bit quantization) on the ImageNet classification task.
  arXiv  Detail & Related papers  (2021-11-24T06:23:06Z)
• OMPQ: Orthogonal Mixed Precision Quantization [64.59700856607017]
  Mixed precision quantization takes advantage of hardware's multiple bit-width arithmetic operations to unleash the full potential of network quantization. We propose to optimize a proxy metric, the concept of networkity, which is highly correlated with the loss of the integer programming. This approach reduces the search time and required data amount by orders of magnitude, with little compromise on quantization accuracy.
  arXiv  Detail & Related papers  (2021-09-16T10:59:33Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• Post-Training Quantization for Vision Transformer [85.57953732941101]
  We present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. We can obtain an 81.29% top-1 accuracy using DeiT-B model on ImageNet dataset with about 8-bit quantization.
  arXiv  Detail & Related papers  (2021-06-27T06:27:22Z)
• One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment [36.75157407486302]
  We propose a method to train a model for all quantization that supports diverse bit-widths. We use wavelet decomposition and reconstruction to increase the diversity of weights. Our method can achieve accuracy comparable to dedicated models trained at the same precision.
  arXiv  Detail & Related papers  (2021-05-04T08:10:50Z)
• n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization [0.0]
  Powers-of-two (PoT) quantization reduces the number of bit operations of deep neural networks on resource-constrained hardware. PoT quantization triggers a severe accuracy drop because of its limited representation ability. We propose an efficient PoT quantization scheme that balances accuracy and costs in a memory-efficient way.
  arXiv  Detail & Related papers  (2021-03-22T10:13:12Z)
• 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)
• DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution Networks [49.191062785007006]
  Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. Existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths, or require a heavy fine-tuning process to recover the performance. We propose a novel distribution-aware quantization scheme (DAQ) which facilitates accurate training-free quantization in ultra-low precision.
  arXiv  Detail & Related papers  (2020-12-21T10:19:42Z)
• Searching for Low-Bit Weights in Quantized Neural Networks [129.8319019563356]
  Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. We present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately.
  arXiv  Detail & Related papers  (2020-09-18T09:13:26Z)
• Least squares binary quantization of neural networks [19.818087225770967]
  We focus on the binary quantization, in which values are mapped to -1 and 1. Inspired by the pareto-optimality of 2-bits versus 1-bit quantization, we introduce a novel 2-bits quantization with provably least squares error.
  arXiv  Detail & Related papers  (2020-01-09T00:01:14Z)

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.