paper-with-me

Papers

Is Integer Arithmetic Enough for Deep Learning Training?

2022-07-18 · Alireza Ghaffari, Marzieh S. Tahaei, Mohammadreza Tayaranian, Masoud Asgharian, Vahid Partovi Nia

The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point arithmetic with low-bit integer arithmetic is a promising approach to save energy, memory footprint, and latency of deep learning models. As such, quantization has attracted the attention of researchers in recent years. However, using integer numbers to form a fully functional integer training pipeline including forward pass, back-propagation, and stochastic gradient descent is not studied in detail. Our empirical and mathematical results reveal that integer arithmetic seems to be enough to train deep learning models. Unlike recent proposals, instead of quantization, we directly switch the number representation of computations. Our novel training method forms a fully integer training pipeline that does not change the trajectory of the loss and accuracy compared to floating-point, nor does it need any special hyper-parameter tuning, distribution adjustment, or gradient clipping. Our experimental results show that our proposed method is effective in a wide variety of tasks such as classification (including vision transformers), object detection, and semantic segmentation.

📄 PDF Abstract BibTeX arXiv:2207.08822

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learningobject-detectionObject DetectionQuantizationSemantic Segmentation

Similar Papers 제목 키워드 기반

NITI: Training Integer Neural Networks Using Integer-only Arithmetic

2020-09-28 · Maolin Wang, Seyedramin Rasoulinezhad, Philip H. W. Leong, Hayden K. -H. So

While integer arithmetic has been widely adopted for improved performance in deep quantized neural network inference, training remains a task primarily executed using floating point arithmetic. This is because both high …

I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

2022-07-04 · ICCV 2023 1 · Zhikai Li, Qingyi Gu

Vision Transformers (ViTs) have achieved state-of-the-art performance on various computer vision applications. However, these models have considerable storage and computational overheads, making their deployment and effi…

Quantization

Arithmetic addition of two integers by deep image classification networks: experiments to quantify their autonomous reasoning ability

2019-12-10 · Shuaicheng Liu, Zehao Zhang, Kai Song, Bing Zeng

The unprecedented performance achieved by deep convolutional neural networks for image classification is linked primarily to their ability of capturing rich structural features at various layers within networks. Here we …

General Classificationimage-classificationImage Classification

Scaling Integer Arithmetic in Probabilistic Programs

2023-07-25 · William X. Cao, Poorva Garg, Ryan Tjoa, Steven Holtzen 외

Distributions on integers are ubiquitous in probabilistic modeling but remain challenging for many of today's probabilistic programming languages (PPLs). The core challenge comes from discrete structure: many of today's …

Probabilistic Programming

Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation

2022-09-20 · Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh 외

The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously researchers were focused on lower bit-wi…