English
Related papers

Related papers: Regularized Classification-Aware Quantization

200 papers

Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes. Contemporary studies on DNN imply that such sample difference is rooted on the distribution of intrinsic pattern…

Machine Learning · Computer Science 2021-08-19 Chi Zhang , Xiaoning Ma , Yu Liu , Le Wang , Yuanqi Su , Yuehu Liu

We provide the first analysis of a non-trivial quantization scheme for compressed sensing measurements arising from structured measurements. Specifically, our analysis studies compressed sensing matrices consisting of rows selected at…

Information Theory · Computer Science 2017-02-16 Joe-Mei Feng , Felix Krahmer , Rayan Saab

Time series anomaly detection is instrumental in maintaining system availability in various domains. Current work in this research line mainly focuses on learning data normality deeply and comprehensively by devising advanced neural network…

Machine Learning · Computer Science 2024-04-25 Hongzuo Xu , Yijie Wang , Songlei Jian , Qing Liao , Yongjun Wang , Guansong Pang

This paper proposes Quantizable DNNs, a special type of DNNs that can flexibly quantize its bit-width (denoted as `bit modes' thereafter) during execution without further re-training. To simultaneously optimize for all bit modes, a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Kunyuan Du , Ya Zhang , Haibing Guan

Classification is the task of predicting the class labels of objects based on the observation of their features. In contrast, quantification has been defined as the task of determining the prevalences of the different sorts of class labels…

Machine Learning · Statistics 2016-08-15 Dirk Tasche

We design a distributed function-aware quantization scheme for distributed functional compression. We consider $2$ correlated sources $X_1$ and $X_2$ and a destination that seeks an estimate $\hat{f}$ for the outcome of a continuous…

Information Theory · Computer Science 2023-01-24 Derya Malak , Muriel Médard

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

Machine Learning · Computer Science 2018-02-02 Chen Xu , Jianqiang Yao , Zhouchen Lin , Wenwu Ou , Yuanbin Cao , Zhirong Wang , Hongbin Zha

In this paper, we consider a regularization strategy for the factorization method when there is noise added to the data operator. The factorization method is a qualitative method used in shape reconstruction problems. These methods are…

Analysis of PDEs · Mathematics 2023-04-05 Isaac Harris

We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Bohan Zhuang , Chunhua Shen , Mingkui Tan , Peng Chen , Lingqiao Liu , Ian Reid

Learning algorithms that learn linear models often have high representation bias on real-world problems. In this paper, we show that this representation bias can be greatly reduced by discretization. Discretization is a common procedure in…

Machine Learning · Computer Science 2017-01-26 Nayyar A. Zaidi , Yang Du , Geoffrey I. Webb

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Hongwei Xie , Shuo Zhang , Huanghao Ding , Yafei Song , Baitao Shao , Conggang Hu , Ling Cai , Mingyang Li

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the…

Machine Learning · Computer Science 2022-07-08 Huabin Diao , Gongyan Li , Shaoyun Xu , Yuexing Hao

Quantile normalisation is a popular normalisation method for data subject to unwanted variations such as images, speech, or genomic data. It applies a monotonic transformation to the feature values of each sample to ensure that after…

Machine Learning · Statistics 2017-06-02 Marine Le Morvan , Jean-Philippe Vert

We investigate different methods for regularizing quantile regression when predicting either a subset of quantiles or the full inverse CDF. We show that minimizing an expected pinball loss over a continuous distribution of quantiles is a…

Machine Learning · Statistics 2021-02-11 Taman Narayan , Serena Wang , Kevin Canini , Maya Gupta

Sampling and quantization are crucial in digital signal processing, but quantization introduces errors, particularly due to distribution mismatch between input signals and quantizers. Existing methods to reduce this error require precise…

Signal Processing · Electrical Eng. & Systems 2024-09-09 Aman Rishal Chemmala , Satish Mulleti

Quantized neural networks typically require smaller memory footprints and lower computation complexity, which is crucial for efficient deployment. However, quantization inevitably leads to a distribution divergence from the original…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Runpei Dong , Zhanhong Tan , Mengdi Wu , Linfeng Zhang , Kaisheng Ma

The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce…

Optimization and Control · Mathematics 2019-07-15 Soroosh Shafieezadeh-Abadeh , Daniel Kuhn , Peyman Mohajerin Esfahani

In this paper, we study the randomized distributed coordinate descent algorithm with quantized updates. In the literature, the iteration complexity of the randomized distributed coordinate descent algorithm has been characterized under the…

Machine Learning · Statistics 2017-01-23 Mostafa El Gamal , Lifeng Lai

Quantization is emerging as an efficient approach to promote hardware-friendly deep learning and run deep neural networks on resource-limited hardware. However, it still causes a significant decrease to the network in accuracy. We summarize…

Machine Learning · Computer Science 2021-12-03 Haotong Qin

This paper investigates system identification problems with Gaussian inputs and quantized observations under fixed thresholds. By reinterpreting the nonlinear effects induced by quantization as the product of the unknown parameter and an…

Optimization and Control · Mathematics 2025-10-20 Xingrui Liu , Ying Wang , Yanlong Zhao