Aditya Devarakonda
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Aditya Devarakonda has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
James Demmel
3 shared publications- Grey Ballard
Department of Computer Science, Wake Forest University, Winston-Salem, NC 27106 USA
2 shared publications - Ivan Rodero
Rutgers University
2 shared publications - James Demmel
University of California
2 shared publications Kimon Fountoulakis
2 shared publicationsManish Parashar
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 282-292
High-Performance Star-M SVD for Big Data Compression
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 282-292
Open AccessHigh-Performance Star-M SVD for Big Data Compression
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1800-1815
Parallel Rank-Adaptive Higher Order Orthogonal Iteration
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1800-1815
Open AccessParallel Rank-Adaptive Higher Order Orthogonal Iteration
- Open Access
- 19 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 52-63
Scalable Dual Coordinate Descent for Kernel Methods
- 19 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 52-63
Open AccessScalable Dual Coordinate Descent for Kernel Methods
- 2 January 2019
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 41 (1) , C1-C27
Avoiding Communication in Primal and Dual Block Coordinate Descent Methods
Primal and dual block coordinate descent methods are iterative methods for solving regularized and unregularized optimization problems. Distributed-memory parallel implementations of these methods have become popular in analyzing large machine learning datasets. However, existing implementations communicate at every iteration, which, on modern data center and supercomputing architectures, often dominates the cost of floating-point computation. Recent results on communication-avoiding Krylov subspace methods suggest that large speedups are possible by re-organizing iterative algorithms to avoid communication. We show how applying similar algorithmic transformations can lead to primal and dual block coordinate descent methods that only communicate every $s$ iterations---where $s$ is a tuning parameter---instead of every iteration for the regularized least-squares problem. We show that the communication-avoiding variants reduce the number of synchronizations by a factor of $s$ on distributed-memory parallel ...- 2 January 2019
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 41 (1) , C1-C27
Avoiding Communication in Primal and Dual Block Coordinate Descent Methods
Primal and dual block coordinate descent methods are iterative methods for solving regularized and unregularized optimization problems. Distributed-memory parallel implementations of these methods have become popular in analyzing large machine learning datasets. However, existing implementations communicate at every iteration, which, on modern data center and supercomputing architectures, often dominates the cost of floating-point computation. Recent results on communication-avoiding Krylov subspace methods suggest that large speedups are possible by re-organizing iterative algorithms to avoid communication. We show how applying similar algorithmic transformations can lead to primal and dual block coordinate descent methods that only communicate every $s$ iterations---where $s$ is a tuning parameter---instead of every iteration for the regularized least-squares problem. We show that the communication-avoiding variants reduce the number of synchronizations by a factor of $s$ on distributed-memory parallel ...- Open Access
- 13 August 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Reducing Communication in Proximal Newton Methods for Sparse Least Squares Problems
- 13 August 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessReducing Communication in Proximal Newton Methods for Sparse Least Squares Problems
- Open Access
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17, 409-418
Avoiding Synchronization in First-Order Methods for Sparse Convex Optimization
Parallel computing has played an important role in speeding up convex optimization methods for big data analytics and large-scale machine learning (ML). However, the scalability of these optimization methods is inhibited by the cost of communicating and synchronizing processors in a parallel setting. Iterative ML methods are particularly sensitive to communication cost since they often require communication every iteration. In this work, we extend well-known techniques from Communication-Avoiding Krylov subspace methods to first-order, block coordinate descent methods for Support Vector Machines and Proximal Least-Squares problems. Our Synchronization-Avoiding (SA) variants reduce the latency cost by a tunable factor of 's' at the expense of a factor of 's' increase in flops and bandwidth costs. We show that the SA-variants are numerically stable and can attain large speedups of up to 5.1x on a Cray XC30 supercomputer.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17, 409-418
Open AccessAvoiding Synchronization in First-Order Methods for Sparse Convex Optimization
Parallel computing has played an important role in speeding up convex optimization methods for big data analytics and large-scale machine learning (ML). However, the scalability of these optimization methods is inhibited by the cost of communicating and synchronizing processors in a parallel setting. Iterative ML methods are particularly sensitive to communication cost since they often require communication every iteration. In this work, we extend well-known techniques from Communication-Avoiding Krylov subspace methods to first-order, block coordinate descent methods for Support Vector Machines and Proximal Least-Squares problems. Our Synchronization-Avoiding (SA) variants reduce the latency cost by a tunable factor of 's' at the expense of a factor of 's' increase in flops and bandwidth costs. We show that the SA-variants are numerically stable and can attain large speedups of up to 5.1x on a Cray XC30 supercomputer.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-213
Matrix factorizations at scale: A comparison of scientific data analytics in spark and C+MPI using three case studies
We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausability), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to 1.6TB particle physics, 2.2TB and 16TB climate modeling and 1.1TB bioimaging data. The data matrices are tall-and-skinny which enable the algorithms to map conveniently into Spark's data-parallel model. We perform scaling experiments on up to 1600 Cray XC40 nodes, describe the sources of slowdowns, and provide tuning guidance to obtain high performance.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-213
Matrix factorizations at scale: A comparison of scientific data analytics in spark and C+MPI using three case studies
We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausability), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to 1.6TB particle physics, 2.2TB and 16TB climate modeling and 1.1TB bioimaging data. The data matrices are tall-and-skinny which enable the algorithms to map conveniently into Spark's data-parallel model. We perform scaling experiments on up to 1600 Cray XC40 nodes, describe the sources of slowdowns, and provide tuning guidance to obtain high performance.
- Open Access
- 13 July 2014
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Architecting an autograder for parallel code
- 13 July 2014
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessArchitecting an autograder for parallel code
- 12 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computing in Science & Engineering
- Vol. 15 (4) , 10-18
Cloud Paradigms and Practices for Computational and Data-Enabled Science and Engineering
Clouds are rapidly joining high-performance computing (HPC) systems, clusters, and grids as viable platforms for scientific exploration and discovery. As a result, understanding application formulations and usage modes that are meaningful in such a hybrid infrastructure, and how application workflows can effectively utilize it, is critical. Here, three hybrid HPC/grid and cloud cyber infrastructure usage modes are explored: HPC in the Cloud, HPC plus Cloud, and HPC as a Service, presenting illustrative scenarios in each case and outlining benefits, limitations, and research challenges.
- 12 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computing in Science & Engineering
- Vol. 15 (4) , 10-18
Cloud Paradigms and Practices for Computational and Data-Enabled Science and Engineering
Clouds are rapidly joining high-performance computing (HPC) systems, clusters, and grids as viable platforms for scientific exploration and discovery. As a result, understanding application formulations and usage modes that are meaningful in such a hybrid infrastructure, and how application workflows can effectively utilize it, is critical. Here, three hybrid HPC/grid and cloud cyber infrastructure usage modes are explored: HPC in the Cloud, HPC plus Cloud, and HPC as a Service, presenting illustrative scenarios in each case and outlining benefits, limitations, and research challenges.
- Top Cited Papers
- 1 September 2012
- Published by Elsevier in Journal of Computer and System Sciences
- Vol. 78 (5) , 1330-1344
Cloud federation in a layered service model
- 1 September 2012
- Published by Elsevier in Journal of Computer and System Sciences
- Vol. 78 (5) , 1330-1344
Top Cited PapersCloud federation in a layered service model