English
Related papers

Related papers: FleXOR: Trainable Fractional Quantization

200 papers

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target…

Machine Learning · Computer Science 2022-07-25 Andrey Kuzmin , Mart van Baalen , Markus Nagel , Arash Behboodi

Quantum machine learning applies principles such as superposition and entanglement to data processing and optimization. Variational quantum models operate on qubits in high-dimensional Hilbert spaces and provide an alternative approach to…

Machine Learning · Computer Science 2026-03-02 Miras Seilkhan , Adilbek Taizhanov

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model…

Cryptography and Security · Computer Science 2025-10-28 Gokulnath Rajendran , Suman Deb , Anupam Chattopadhyay

Reducing bit-widths of activations and weights of deep networks makes it efficient to compute and store them in memory, which is crucial in their deployments to resource-limited devices, such as mobile phones. However, decreasing bit-widths…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Sangil Jung , Changyong Son , Seohyung Lee , Jinwoo Son , Youngjun Kwak , Jae-Joon Han , Sung Ju Hwang , Changkyu Choi

Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster…

Machine Learning · Computer Science 2018-02-01 Angus Galloway , Graham W. Taylor , Medhat Moussa

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

Machine Learning · Computer Science 2018-05-30 Dongsoo Lee , Byeongwook Kim

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-10-14 Prateeth Nayak , David Zhang , Sek Chai

The quantization of neural networks for the mitigation of the nonlinear and components' distortions in dual-polarization optical fiber transmission is studied. Two low-complexity neural network equalizers are applied in three 16-QAM 34.4…

Signal Processing · Electrical Eng. & Systems 2023-10-11 Jamal Darweesh , Nelson Costa , Antonio Napoli , Bernhard Spinnler , Yves Jaouen , Mansoor Yousefi

Approximate model counting for bit-vector SMT formulas (generalizing \#SAT) has many applications such as probabilistic inference and quantitative information-flow security, but it is computationally difficult. Adding random parity…

Cryptography and Security · Computer Science 2017-12-22 Seonmo Kim , Stephen McCamant

Quantum machine learning aspires to overcome intractability that currently limits its applicability to practical problems. However, quantum machine learning itself is limited by low effective dimensions achievable in state-of-the-art…

Quantum Physics · Physics 2022-01-04 Kunkun Wang , Lei Xiao , Wei Yi , Shi-Ju Ran , Peng Xue

Convolutional neural networks excel in image recognition tasks, but this comes at the cost of high computational and memory complexity. To tackle this problem, [1] developed a tensor factorization framework to compress fully-connected…

Machine Learning · Computer Science 2016-11-11 Timur Garipov , Dmitry Podoprikhin , Alexander Novikov , Dmitry Vetrov

The advent of noisy-intermediate scale quantum computers has introduced the exciting possibility of achieving quantum speedups in machine learning tasks. These devices, however, are composed of a small number of qubits, and can faithfully…

Quantum Physics · Physics 2023-08-24 Rohit Dilip , Yu-Jie Liu , Adam Smith , Frank Pollmann

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Machine Learning · Statistics 2026-05-19 Mehmet Aktukmak , Daniel Huang , Ke Ding

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…

Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the performance of the original…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Geon Park , Jaehong Yoon , Haiyang Zhang , Xing Zhang , Sung Ju Hwang , Yonina C. Eldar

Deploying Deep Neural Networks in low-power embedded devices for real time-constrained applications requires optimization of memory and computational complexity of the networks, usually by quantizing the weights. Most of the existing works…

Machine Learning · Computer Science 2022-03-11 Dominika Przewlocka-Rus , Syed Shakib Sarwar , H. Ekin Sumbul , Yuecheng Li , Barbara De Salvo

Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, embed data and trainable parameters into gate-based operations and optimize the parameters…

Quantum Physics · Physics 2026-04-09 Basil Kyriacou , Mo Kordzanganeh , Maniraman Periyasamy , Alexey Melnikov

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

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

Computer Vision and Pattern Recognition · Computer Science 2017-09-20 Mu Li , Wangmeng Zuo , Shuhang Gu , Debin Zhao , David Zhang

Quantum computers require precise control over parameters and careful engineering of the underlying physical system. In contrast, neural networks have evolved to tolerate imprecision and inhomogeneity. Here, using a reservoir computing…

Quantum Physics · Physics 2021-12-13 Sanjib Ghosh , Tanjung Krisnanda , Tomasz Paterek , Timothy C. H. Liew