English
Related papers

Related papers: Stochastic Parameter Decomposition

200 papers

Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networks (ANNs). However, the training of SNN usually relies on surrogate gradients due to the…

Neural and Evolutionary Computing · Computer Science 2026-05-11 Himanshu Udupi , Xiaocong Yang , ChengXiang Zhai

Classical model reduction techniques project the governing equations onto a linear subspace of the original state space. More recent data-driven techniques use neural networks to enable nonlinear projections. Whilst those often enable…

Numerical Analysis · Mathematics 2024-06-19 Tjeerd Jan Heeringa , Christoph Brune , Mengwu Guo

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Computation and Language · Computer Science 2026-05-27 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

The increasing size of deep learning models has made distributed training across multiple devices essential. However, current methods such as distributed data-parallel training suffer from large communication and synchronization overheads…

Machine Learning · Computer Science 2025-02-10 Cabrel Teguemne Fokam , Khaleelulla Khan Nazeer , Lukas König , David Kappel , Anand Subramoney

Stochastic gradient methods enable learning probabilistic models from large amounts of data. While large step-sizes (learning rates) have shown to be best for least-squares (e.g., Gaussian noise) once combined with parameter averaging,…

Machine Learning · Statistics 2018-11-22 Dmitry Babichev , Francis Bach

Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models.…

Computation and Language · Computer Science 2017-12-25 Zhongliang Li , Raymond Kulhanek , Shaojun Wang , Yunxin Zhao , Shuang Wu

Deep neural networks have significantly alleviated the burden of feature engineering, but comparable efforts are now required to determine effective architectures for these networks. Furthermore, as network sizes have become excessively…

Machine Learning · Computer Science 2023-10-25 Yognjin Lee

Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This…

Machine Learning · Computer Science 2025-03-18 Yaochen Hu , Mai Zeng , Ge Zhang , Pavel Rumiantsev , Liheng Ma , Yingxue Zhang , Mark Coates

Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no…

Machine Learning · Computer Science 2019-02-26 Yibo Lin , Zhao Song , Lin F. Yang

This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In…

Neural and Evolutionary Computing · Computer Science 2018-02-14 Dianhui Wang , Ming Li

In this paper, we apply the Feature Space Decomposition (FSD) method developed in [LS24, GLS25, LSSW26, ALSS26] to obtain, under fairly general conditions, matching upper and lower bounds for the population excess risk of spectral methods…

Statistics Theory · Mathematics 2026-05-18 Guillaume Lecué , Zhifan Li , Zong Shang

The numerical solution of large-scale PDEs, such as those occurring in data-driven applications, unavoidably require powerful parallel computers and tailored parallel algorithms to make the best possible use of them. In fact, considerations…

Numerical Analysis · Mathematics 2017-05-11 Francisco Bernal , Gonçalo dos Reis , Greig Smith

Numerical resolution of high-dimensional nonlinear PDEs remains a huge challenge due to the curse of dimensionality. Starting from the weak formulation of the Lawson-Euler scheme, this paper proposes a stochastic particle method (SPM) by…

Numerical Analysis · Mathematics 2025-02-11 Zhengyang Lei , Sihong Shao , Yunfeng Xiong

Large Language Models (LLMs) have achieved remarkable breakthroughs. However, the huge number of parameters in LLMs require significant amount of memory storage in inference, which prevents their practical deployment in many applications.…

Computation and Language · Computer Science 2024-10-08 Jingcun Wang , Yu-Guang Chen , Ing-Chao Lin , Bing Li , Grace Li Zhang

Fully connected layers are a primary source of memory and computational overhead in deep neural networks due to their dense, often redundant parameterization. While various compression techniques exist, they frequently introduce complex…

Machine Learning · Computer Science 2025-12-16 Maksymilian Szorc

Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also important for…

Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all…

Numerical Analysis · Computer Science 2018-10-04 Eran Treister , Lars Ruthotto , Michal Sharoni , Sapir Zafrani , Eldad Haber

Least squares deconvolution (LSD) is a powerful method of extracting high-precision average line profiles from the stellar intensity and polarization spectra. Despite its common usage, the LSD method is poorly documented and has never been…

Solar and Stellar Astrophysics · Physics 2015-05-19 O. Kochukhov , V. Makaganiuk , N. Piskunov

Stochastic Gradient Descent (SGD) is the key learning algorithm for many machine learning tasks. Because of its computational costs, there is a growing interest in accelerating SGD on HPC resources like GPU clusters. However, the…

Machine Learning · Computer Science 2021-01-20 Peng Jiang , Gagan Agrawal

Statistic modeling and data-driven learning are the two vital fields that attract many attentions. Statistic models intend to capture and interpret the relationships among variables, while data-based learning attempt to extract information…

Machine Learning · Computer Science 2021-12-22 Jingwei Li