English
Related papers

Related papers: Training with Quantization Noise for Extreme Model…

200 papers

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

Machine Learning · Computer Science 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitigate these problems, provided that model performance stays…

Machine Learning · Computer Science 2025-05-27 Alexander Conzelmann , Robert Bamler

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zekang Zheng , Haokun Li , Yaofo Chen , Mingkui Tan , Qing Du

Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks. This…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Junjie Liu , Dongchao Wen , Deyu Wang , Wei Tao , Tse-Wei Chen , Kinya Osa , Masami Kato

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…

Machine Learning · Computer Science 2020-05-08 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

Machine Learning · Computer Science 2022-10-26 Christopher Subia-Waud , Srinandan Dasmahapatra

Model quantization enables the deployment of deep neural networks under resource-constrained devices. Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings, i.e., codewords, while the…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Dan Liu , Xi Chen , Chen Ma , Xue Liu

The discontinuous operations inherent in quantization and sparsification introduce a long-standing obstacle to backpropagation, particularly in ultra-low precision and sparse regimes. While the community has long viewed quantization as…

Machine Learning · Computer Science 2026-03-11 Chengxi Ye , Grace Chu , Yanfeng Liu , Yichi Zhang , Lukasz Lew , Li Zhang , Mark Sandler , Andrew Howard

Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle this challenge, the straight-through estimator (STE) has become the most widely adopted…

Machine Learning · Computer Science 2025-05-26 Halyun Jeong , Jack Xin , Penghang Yin

Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically overlook the relationship between a well-trained NN and the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Peng Xia , Junbiao Pang , Tianyang Cai

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

While model compression is increasingly important because of large neural network size, compression-aware training is challenging as it needs sophisticated model modifications and longer training time.In this paper, we introduce…

Machine Learning · Computer Science 2021-05-06 Dongsoo Lee , Se Jung Kwon , Byeongwook Kim , Jeongin Yun , Baeseong Park , Yongkweon Jeon

Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural…

Machine Learning · Computer Science 2023-06-14 Anshul Nasery , Hardik Shah , Arun Sai Suggala , Prateek Jain

Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Dohyung Kim , Junghyup Lee , Jeimin Jeon , Jaehyeon Moon , Bumsub Ham

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Ximeng Sun , Rameswar Panda , Chun-Fu Chen , Naigang Wang , Bowen Pan , Kailash Gopalakrishnan , Aude Oliva , Rogerio Feris , Kate Saenko

Weight initialization plays a crucial role in the optimization behavior and convergence efficiency of neural networks. Most existing initialization methods, such as Xavier and Kaiming initializations, rely on random sampling and do not…

Machine Learning · Computer Science 2026-02-09 Shaowen Wang , Tariq Alkhalifah

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

Machine Learning · Computer Science 2020-04-08 Matan Haroush , Itay Hubara , Elad Hoffer , Daniel Soudry

Large language models (LLMs) require immense resources for training and inference. Quantization, a technique that reduces the precision of model parameters, offers a promising solution for improving LLM efficiency and sustainability. While…

Machine Learning · Computer Science 2025-02-18 Jacob Nielsen , Peter Schneider-Kamp , Lukas Galke