paper-with-me

홈 › Papers

A Greedy Algorithm for Quantizing Neural Networks

2020-10-29 · Eric Lybrand, Rayan Saab

We propose a new computationally efficient method for quantizing the weights of pre- trained neural networks that is general enough to handle both multi-layer perceptrons and convolutional neural networks. Our method deterministically quantizes layers in an iterative fashion with no complicated re-training required. Specifically, we quantize each neuron, or hidden unit, using a greedy path-following algorithm. This simple algorithm is equivalent to running a dynamical system, which we prove is stable for quantizing a single-layer neural network (or, alternatively, for quantizing the first layer of a multi-layer network) when the training data are Gaussian. We show that under these assumptions, the quantization error decays with the width of the layer, i.e., its level of over-parametrization. We provide numerical experiments, on multi-layer networks, to illustrate the performance of our methods on MNIST and CIFAR10 data, as well as for quantizing the VGG16 network using ImageNet data.

📄 PDF Abstract BibTeX arXiv:2010.15979

Code (1)

elybrand/quantized_neural_networks 공식 구현 tf

Tasks

Quantization

Similar Papers 제목 키워드 기반

OPTIMAL BINARY QUANTIZATION FOR DEEP NEURAL NETWORKS

2019-09-25 · Hadi Pouransari, Oncel Tuzel

Quantizing weights and activations of deep neural networks results in significant improvement in inference efficiency at the cost of lower accuracy. A source of the accuracy gap between full precision and quantized model…

Quantization

SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization

2023-09-20 · Jinjie Zhang, Rayan Saab

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive …

Quantization

AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks

2023-04-07 · Cheng Gong, Ye Lu, Surong Dai, Deng Qian 외

Exploring the expected quantizing scheme with suitable mixed-precision policy is the key point to compress deep neural networks (DNNs) in high efficiency and accuracy. This exploration implies heavy workloads for domain …

Neural Architecture SearchQuantization

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

2024-03-11 · Aozhong zhang, Zi Yang, Naigang Wang, Yingyong Qi 외

Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterpart…

Quantization

A simple approach for quantizing neural networks

2022-09-07 · Johannes Maly, Rayan Saab

In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network layers via memoryless scalar quantization…

Quantization