English
Related papers

Related papers: A unified analysis framework for iterative paralle…

200 papers

In this paper, we discuss software design issues related to the development of parallel computational intelligence algorithms on multi-core CPUs, using the new Java 8 functional programming features. In particular, we focus on probabilistic…

Artificial Intelligence · Computer Science 2017-07-10 Andres R. Masegosa , Ana M. Martinez , Hanen Borchani

Asynchronous parallel implementations of stochastic gradient (SG) have been broadly used in solving deep neural network and received many successes in practice recently. However, existing theories cannot explain their convergence and…

Optimization and Control · Mathematics 2019-04-22 Xiangru Lian , Yijun Huang , Yuncheng Li , Ji Liu

While Graph Neural Networks (GNNs) are popular in the deep learning community, they suffer from several challenges including over-smoothing, over-squashing, and gradient vanishing. Recently, a series of models have attempted to relieve…

Machine Learning · Computer Science 2022-11-18 Junxiang Wang , Hongyi Li , Zheng Chai , Yongchao Wang , Yue Cheng , Liang Zhao

We present a new parallel algorithm for probabilistic graphical model optimization. The algorithm relies on data-parallel primitives (DPPs), which provide portable performance over hardware architecture. We evaluate results on CPUs and GPUs…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-09-14 Brenton Lessley , Talita Perciano , Colleen Heinemann , David Camp , Hank Childs , E. Wes Bethel

In the recent years we have witnessed a rapid development of new algorithmic techniques for parameterized algorithms for graph separation problems. We present experimental evaluation of two cornerstone theoretical results in this area:…

Data Structures and Algorithms · Computer Science 2018-11-20 Marcin Pilipczuk , Michał Ziobro

Parallelization is a popular strategy for improving the performance of iterative algorithms. Optimization methods are no exception: design of efficient parallel optimization methods and tight analysis of their theoretical properties are…

Optimization and Control · Mathematics 2023-11-28 Alexander Tyurin , Peter Richtárik

We present an adaptive methodology for the solution of (linear and) non-linear time dependent problems that is especially tailored for massively parallel computations. The basic concept is to solve for large blocks of space-time unknowns…

Computational Physics · Physics 2016-08-30 Robert Dyja , Baskar Ganapathysubramanian , Kristoffer G. van der Zee

Parallelizing Gated Recurrent Unit (GRU) networks is a challenging task, as the training procedure of GRU is inherently sequential. Prior efforts to parallelize GRU have largely focused on conventional parallelization strategies such as…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Gordon Euhyun Moon , Eric C. Cyr

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Machine Learning · Computer Science 2019-12-02 Julia El Zini , Yara Rizk , Mariette Awad

We present a method for fast and accurate physics-based predictions during non-prehensile manipulation planning and control. Given an initial state and a sequence of controls, the problem of predicting the resulting sequence of states is a…

Robotics · Computer Science 2022-03-02 Wisdom C. Agboh , Daniel Ruprecht , Mehmet R. Dogar

Existing Deep Learning frameworks exclusively use either Parameter Server(PS) approach or MPI parallelism. In this paper, we discuss the drawbacks of such approaches and propose a generic framework supporting both PS and MPI programming…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-01-12 Amith R Mamidala , Georgios Kollias , Chris Ward , Fausto Artico

Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and…

Machine Learning · Computer Science 2014-08-12 Yucheng Low , Joseph E. Gonzalez , Aapo Kyrola , Danny Bickson , Carlos E. Guestrin , Joseph Hellerstein

Given a graphical model (GM), computing its partition function is the most essential inference task, but it is computationally intractable in general. To address the issue, iterative approximation algorithms exploring certain local…

Machine Learning · Computer Science 2019-05-15 Sejun Park , Eunho Yang , Se-Young Yun , Jinwoo Shin

Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and…

Machine Learning · Computer Science 2010-06-28 Yucheng Low , Joseph Gonzalez , Aapo Kyrola , Danny Bickson , Carlos Guestrin , Joseph M. Hellerstein

Time-parallel methods can reduce the wall clock time required for the accurate numerical solution of differential equations by parallelizing across the time-dimension. In this paper, we present and test the convergence behavior of a…

Numerical Analysis · Mathematics 2025-02-03 Ignace Bossuyt , Giovanni Samaey , Stefan Vandewalle

This paper considers flow problems in multiscale heterogeneous porous media. The multiscale nature of the modeled process significantly complicates numerical simulations due to the need to compute huge and ill-conditioned sparse matrices,…

Numerical Analysis · Mathematics 2024-10-16 Djulustan Nikiforov , Leonardo A. Poveda , Dmitry Ammosov , Yesy Sarmiento , Juan Galvis

Resource constrained project scheduling is an important combinatorial optimisation problem with many practical applications. With complex requirements such as precedence constraints, limited resources, and finance-based objectives, finding…

Neural and Evolutionary Computing · Computer Science 2022-10-21 Dhananjay R. Thiruvady , Su Nguyen , Christian Blum , Andreas T. Ernst

We introduce a time-parallel algorithm for solving numerically almost integrable Hamiltonian systems in action-angle coordinates. This algorithm is a refinement of that introduced by Saha, Stadel and Tremaine in 1997 (SST97) for the same…

Numerical Analysis · Computer Science 2011-06-21 Hugo Jiménez-Pérez , Jacques Laskar

Multiresolution Matrix Factorization (MMF) was recently introduced as a method for finding multiscale structure and defining wavelets on graphs/matrices. In this paper we derive pMMF, a parallel algorithm for computing the MMF…

Numerical Analysis · Computer Science 2015-07-17 Risi Kondor , Nedelina Teneva , Pramod K. Mudrakarta

We present a methodology for parallel acceleration of learning in the presence of matrix orthogonality and unitarity constraints of interest in several branches of machine learning. We show how an apparently sequential elementary rotation…

Machine Learning · Computer Science 2021-06-02 Firas Hamze