English
Related papers

Related papers: Multiplication-Free Transformer Training via Piece…

200 papers

To improve federated training of neural networks, we develop FedSparsify, a sparsification strategy based on progressive weight magnitude pruning. Our method has several benefits. First, since the size of the network becomes increasingly…

Machine Learning · Computer Science 2023-05-17 Dimitris Stripelis , Umang Gupta , Greg Ver Steeg , Jose Luis Ambite

In the multi-cell multiuser multi-input multi-output (MU-MIMO) systems, fractional programming (FP) has demonstrated considerable effectiveness in optimizing beamforming vectors, yet it suffers from high computational complexity. Recent…

Signal Processing · Electrical Eng. & Systems 2026-01-13 Zihan Jiao , Xinping Yi , Shi Jin

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Computation and Language · Computer Science 2023-04-07 Guorun Wang , Jun Yang , Yaoru Sun

Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for training these models…

Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…

Machine Learning · Computer Science 2023-11-10 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Binarization is a powerful compression technique for neural networks, significantly reducing FLOPs, but often results in a significant drop in model performance. To address this issue, partial binarization techniques have been developed,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Udbhav Bamba , Neeraj Anand , Saksham Aggarwal , Dilip K. Prasad , Deepak K. Gupta

Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (CPA)…

Machine Learning · Computer Science 2026-05-13 Xuan Qi , Yi Wei , Fanqi Yu , Furao Shen , Vittorio Murino , Cigdem Beyan

Operators devoid of multiplication, such as Shift and Add, have gained prominence for their compatibility with hardware. However, neural networks (NNs) employing these operators typically exhibit lower accuracy compared to conventional NNs…

Machine Learning · Computer Science 2024-07-04 Yipin Guo , Zihao Li , Yilin Lang , Qinyuan Ren

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Amelie Royer , Christoph H. Lampert

Quantization using a small number of bits shows promise for reducing latency and memory usage in deep neural networks. However, most quantization methods cannot readily handle complicated functions such as exponential and square root, and…

Image and Video Processing · Electrical Eng. & Systems 2023-03-27 Yangyang Chang , Gerald E. Sobelman

To reduce the computational cost of convolutional neural networks (CNNs) on resource-constrained devices, structured pruning approaches have shown promise in lowering floating-point operations (FLOPs) without substantial drops in accuracy.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Lukas Meiner , Jens Mehnert , Alexandru Paul Condurache

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This…

Computation and Language · Computer Science 2024-07-23 Luyu Qiu , Jianing Li , Chi Su , Chen Jason Zhang , Lei Chen

Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine learning. The classical training method requires paying…

Machine Learning · Computer Science 2021-10-12 Zhao Song , Shuo Yang , Ruizhe Zhang

Optimization-based solvers play a central role in a wide range of signal processing and communication tasks. However, their applicability in latency-sensitive systems is limited by the sequential nature of iterative methods and the high…

Signal Processing · Electrical Eng. & Systems 2026-03-12 Dvir Avrahami , Amit Milstein , Caroline Chaux , Tirza Routtenberg , Nir Shlezinger

Modern Convolutional Neural Networks (CNNs) are complex, encompassing millions of parameters. Their deployment exerts computational, storage and energy demands, particularly on embedded platforms. Existing approaches to prune or sparsify…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Amir H. Ashouri , Tarek S. Abdelrahman , Alwyn Dos Remedios

1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training…

Computation and Language · Computer Science 2026-05-19 Zhijun Tu , Jian Li , Yuanyuan Xi , Siqi Liu , Chuanjian Liu , Hanting Chen , Jie Hu , Yunhe Wang

Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model…

Machine Learning · Computer Science 2026-05-12 Yi Wei , Xuan Qi , Furao Shen

Affine matrix rank minimization problem is a fundamental problem with a lot of important applications in many fields. It is well known that this problem is combinatorial and NP-hard in general. In this paper, a continuous promoting low rank…

Optimization and Control · Mathematics 2017-05-02 Angang Cui , Jigen Peng , Haiyang Li , Chengyi Zhang , Yongchao Yu

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Hannes Fassold

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number…

Machine Learning · Computer Science 2018-11-14 Louis Kirsch , Julius Kunze , David Barber