paper-with-me

홈 › Papers

Training Neural Networks in Single vs Double Precision

2022-09-15 · Tomas Hrycej, Bernhard Bermeitinger, Siegfried Handschuh

The commitment to single-precision floating-point arithmetic is widespread in the deep learning community. To evaluate whether this commitment is justified, the influence of computing precision (single and double precision) on the optimization performance of the Conjugate Gradient (CG) method (a second-order optimization algorithm) and RMSprop (a first-order algorithm) has been investigated. Tests of neural networks with one to five fully connected hidden layers and moderate or strong nonlinearity with up to 4 million network parameters have been optimized for Mean Square Error (MSE). The training tasks have been set up so that their MSE minimum was known to be zero. Computing experiments have disclosed that single-precision can keep up (with superlinear convergence) with double-precision as long as line search finds an improvement. First-order methods such as RMSprop do not benefit from double precision. However, for moderately nonlinear tasks, CG is clearly superior. For strongly nonlinear tasks, both algorithm classes find only solutions fairly poor in terms of mean square error as related to the output variance. CG with double floating-point precision is superior whenever the solutions have the potential to be useful for the application goal.

📄 PDF Abstract BibTeX arXiv:2209.07219

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…

Similar Papers 제목 키워드 기반

92c/MFlops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster

2019-11-12 · Douglas Aberdeen, Jonathan Baxter, Robert Edwards

Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and fac…

Face Recognition

Curvature-aware dynamic precision approach for physics-informed neural networks

2026-06-03 · Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn, Taniya Kapoor arxiv

Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, recent studies sh…

Computational Efficiency

Training with reduced precision of a support vector machine model for text classification

2020-07-17 · Dominik Żurek, Marcin Pietroń

This paper presents the impact of using quantization on the efficiency of multi-class text classification in the training process of a support vector machine (SVM). This work is focused on comparing the efficiency of SVM…

CPUGeneral ClassificationGPUMulti Class Text Classification+3

Nearly Lossless Adaptive Bit Switching

2025-02-03 · Haiduo Huang, Zhenhua Liu, Tian Xia, Wenzhe Zhao 외

Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width se…

Quantization

Convolutional Neural Networks Quantization with Attention

2022-09-30 · Binyi Wu, Bernd Waschneck, Christian Georg Mayr

It has been proven that, compared to using 32-bit floating-point numbers in the training phase, Deep Convolutional Neural Networks (DCNNs) can operate with low precision during inference, thereby saving memory space and …

Quantization