English
Related papers

Related papers: Sparsifying dimensionality reduction of PDE soluti…

200 papers

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

We propose a learning framework based on stochastic Bregman iterations, also known as mirror descent, to train sparse neural networks with an inverse scale space approach. We derive a baseline algorithm called LinBreg, an accelerated…

Machine Learning · Computer Science 2022-08-16 Leon Bungert , Tim Roith , Daniel Tenbrinck , Martin Burger

The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of…

Machine Learning · Computer Science 2017-08-03 Hao He , Bo Xin , David Wipf

Sparsity constraints on the control inputs of a linear dynamical system naturally arise in several practical applications such as networked control, computer vision, seismic signal processing, and cyber-physical systems. In this work, we…

Systems and Control · Electrical Eng. & Systems 2024-09-11 Rupam Kalyan Chakraborty , Geethu Joseph , Chandra R. Murthy

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…

Machine Learning · Statistics 2022-08-09 Jonathan Richard Schwarz , Yee Whye Teh

Koopman decomposition is a non-linear generalization of eigen-decomposition, and is being increasingly utilized in the analysis of spatio-temporal dynamics. Well-known techniques such as the dynamic mode decomposition (DMD) and its linear…

Dynamical Systems · Mathematics 2021-05-12 Shaowu Pan , Nicholas Arnold-Medabalimi , Karthik Duraisamy

Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks…

Machine Learning · Computer Science 2017-11-08 Sharan Narang , Erich Elsen , Gregory Diamos , Shubho Sengupta

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

It is often possible to perform reduced order modelling by specifying linear subspace which accurately captures the dynamics of the system. This approach becomes especially appealing when linear subspace explicitly depends on parameters of…

Machine Learning · Computer Science 2026-04-17 Vladimir Fanaskov , Vladislav Trifonov , Alexander Rudikov , Ekaterina Muravleva , Ivan Oseledets

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

Well-established methods for the solution of stochastic partial differential equations (SPDEs) typically struggle in problems with high-dimensional inputs/outputs. Such difficulties are only amplified in large-scale applications where even…

Machine Learning · Statistics 2019-09-10 Constantin Grigo , Phaedon-Stelios Koutsourelakis

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

This paper addresses the structurally-constrained sparse decomposition of multi-dimensional signals onto overcomplete families of vectors, called dictionaries. The contribution of the paper is threefold. Firstly, a generic spatio-temporal…

Data Structures and Algorithms · Computer Science 2016-10-03 Yoann Isaac , Quentin Barthélemy , Cédric Gouy-Pailler , Michèle Sebag , Jamal Atif

Deep ensembles have emerged as a powerful technique for improving predictive performance and enhancing model robustness across various applications by leveraging model diversity. However, traditional deep ensemble methods are often…

Dynamic network reconstruction has been shown to be challenging due to the requirements on sparse network structures and network identifiability. The direct parametric method (e.g., using ARX models) requires a large amount of parameters in…

Systems and Control · Computer Science 2018-11-22 Zuogong Yue , Johan Thunberg , Lennart Ljung , Jorge Goncalves

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

In deep learning it is common to overparameterize neural networks, that is, to use more parameters than training samples. Quite surprisingly training the neural network via (stochastic) gradient descent leads to models that generalize very…

Optimization and Control · Mathematics 2025-01-30 Hung-Hsu Chou , Johannes Maly , Holger Rauhut

This work introduces Directed-Evolution (DE) method for sparsification of neural networks, where the relevance of parameters to the network accuracy is directly assessed and the parameters that produce the least effect on accuracy when…

Machine Learning · Computer Science 2022-06-14 Luiz M Franca-Neto

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the…

Machine Learning · Computer Science 2020-09-22 Negar Foroutan Eghlidi , Martin Jaggi
‹ Prev 1 2 3 10 Next ›