English
Related papers

Related papers: Communication-Optimal Parallel Algorithm for Stras…

200 papers

This thesis is concerned with the design of distributed algorithms for solving optimization problems. We consider networks where each node has exclusive access to a cost function, and design algorithms that make all nodes cooperate to find…

Optimization and Control · Mathematics 2013-12-03 João F. C. Mota

Heavy communication, in particular, collective operations, can become a critical performance bottleneck in scaling the training of billion-parameter neural networks to large-scale parallel systems. This paper introduces a four-dimensional…

Machine Learning · Computer Science 2024-05-15 Siddharth Singh , Prajwal Singhania , Aditya K. Ranjan , Zack Sating , Abhinav Bhatele

Efficient solutions of large-scale, ill-conditioned and indefinite algebraic equations are ubiquitously needed in numerous computational fields, including multiphysics simulations, machine learning, and data science. Because of their…

Mathematical Software · Computer Science 2026-05-25 Xiaoye Sherry Li , Yang Liu

Graph Neural Networks (GNNs) are a computationally efficient method to learn embeddings and classifications on graph data. However, GNN training has low computational intensity, making communication costs the bottleneck for scalability.…

Machine Learning · Computer Science 2025-04-08 Ujjaini Mukhodopadhyay , Alok Tripathy , Oguz Selvitopi , Katherine Yelick , Aydin Buluc

We present a new parallel algorithm for solving triangular systems with multiple right hand sides (TRSM). TRSM is used extensively in numerical linear algebra computations, both to solve triangular linear systems of equations as well as to…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-03-23 Tobias Wicky , Edgar Solomonik , Torsten Hoefler

We study the tradeoff between the statistical error and communication cost of distributed statistical estimation problems in high dimensions. In the distributed sparse Gaussian mean estimation problem, each of the $m$ machines receives $n$…

Machine Learning · Computer Science 2016-05-11 Mark Braverman , Ankit Garg , Tengyu Ma , Huy L. Nguyen , David P. Woodruff

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

Linear-scaling electronic-structure techniques, also called O(N) techniques, rely heavily on the multiplication of sparse matrices, where the sparsity arises from spatial cut-offs. In order to treat very large systems, the calculations must…

Materials Science · Physics 2009-10-31 D. R. Bowler , T. Miyazaki , M. J. Gillan

Reducing communication - either between levels of a memory hierarchy or between processors over a network - is a key component of performance optimization (in both time and energy) for many problems, including dense linear algebra, particle…

Data Structures and Algorithms · Computer Science 2020-03-03 Grace Dinh , James Demmel

A novel parallel algorithm for matrix multiplication is presented. The hyper-systolic algorithm makes use of a one-dimensional processor abstraction. The procedure can be implemented on all types of parallel systems. It can handle…

Mathematical Software · Computer Science 2007-05-23 Thomas Lippert , Nikolay Petkov , Paolo Palazzari , Klaus Schilling

Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the communication overhead for exchanging information such as…

Machine Learning · Computer Science 2017-10-31 Jianqiao Wangni , Jialei Wang , Ji Liu , Tong Zhang

We investigate sparse matrix bipartitioning -- a problem where we minimize the communication volume in parallel sparse matrix-vector multiplication. We prove, by reduction from graph bisection, that this problem is $\mathcal{NP}$-complete…

Data Structures and Algorithms · Computer Science 2020-05-08 Timon E. Knigge , Rob H. Bisseling

Bayesian matrix factorization (BMF) is a powerful tool for producing low-rank representations of matrices and for predicting missing values and providing confidence intervals. Scaling up the posterior inference for massive-scale matrices is…

Machine Learning · Statistics 2019-02-28 Xiangju Qin , Paul Blomstedt , Eemeli Leppäaho , Pekka Parviainen , Samuel Kaski

We propose a fine-grained hypergraph model for sparse matrix-matrix multiplication (SpGEMM), a key computational kernel in scientific computing and data analysis whose performance is often communication bound. This model correctly describes…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-03-18 Grey Ballard , Alex Druinsky , Nicholas Knight , Oded Schwartz

Sparse, irregular graphs show up in various applications like linear algebra, machine learning, engineering simulations, robotic control, etc. These graphs have a high degree of parallelism, but their execution on parallel threads of modern…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-02-17 Nimish Shah , Wannes Meert , Marian Verhelst

Distributed computing excels at processing large scale data, but the communication cost for synchronizing the shared parameters may slow down the overall performance. Fortunately, the interactions between parameter and data in many problems…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-05-19 Mu Li , Dave G. Andersen , Alexander J. Smola

The complexity of matrix multiplication (hereafter MM) has been intensively studied since 1969, when Strassen surprisingly decreased the exponent 3 in the cubic cost of the straightforward classical MM to log 2 (7) $\approx$ 2.8074.…

Symbolic Computation · Computer Science 2016-12-20 Jean-Guillaume Dumas , Victor Pan

We present scalable parallel algorithms with sublinear per-processor communication volume and low latency for several fundamental problems related to finding the most relevant elements in a set, for various notions of relevance: We begin…

Data Structures and Algorithms · Computer Science 2015-10-20 Lorenz Hübschle-Schneider , Peter Sanders , Ingo Müller

In this paper, we propose a distributed algorithm for stochastic smooth, non-convex optimization. We assume a worker-server architecture where $N$ nodes, each having $n$ (potentially infinite) number of samples, collaborate with the help of…

Optimization and Control · Mathematics 2020-11-09 Pranay Sharma , Swatantra Kafle , Prashant Khanduri , Saikiran Bulusu , Ketan Rajawat , Pramod K. Varshney

We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD). Our goal is to…

Machine Learning · Computer Science 2018-05-17 Amir Gholami , Ariful Azad , Peter Jin , Kurt Keutzer , Aydin Buluc