Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Srinivas Eswar"'
Autor:
Ramakrishnan Kannan, Michael A. Matheson, Koby Hayashi, Grey Ballard, Haesun Park, Srinivas Eswar
Publikováno v:
ACM Transactions on Mathematical Software. 47:1-37
We consider the problem of low-rank approximation of massive dense nonnegative tensor data, for example, to discover latent patterns in video and imaging applications. As the size of data sets grows, single workstations are hitting bottlenecks in bot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03314e746b4d51ecf649f73b53da0c08
https://doi.org/10.1145/3432185
https://doi.org/10.1145/3432185
Publikováno v:
Journal of Global Optimization. 81:967-989
A framework is proposed to simultaneously cluster objects and detect anomalies in attributed graph data. Our objective function along with the carefully constructed constraints promotes interpretability of both the clustering and anomaly detection co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa16e9bf096f142f4c81c7e34a020116
https://doi.org/10.1007/s10898-021-01024-z
https://doi.org/10.1007/s10898-021-01024-z
Publikováno v:
SC
We develop the first distributed-memory parallel implementation of Symmetric Nonnegative Matrix Factorization (SymNMF), a key data analytics kernel for clustering and dimensionality reduction. Our implementation includes two different algorithms for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::621b52b228adb5f586e5d9a83a8aa845
https://doi.org/10.1109/sc41405.2020.00078
https://doi.org/10.1109/sc41405.2020.00078
Autor:
Jiajia Li, Ümit V. Çatalyürek, Rich Vuduc, Jeffrey Young, Bora Uçar, Eric R. Hein, Abdurrahman Yasar, Srinivas Eswar, Jason Riedy, Thomas M. Conte
Publikováno v:
ACM Transactions on Parallel Computing
ACM Transactions on Parallel Computing, Association for Computing Machinery, 2020, 7 (4), pp.1-25. ⟨10.1145/3418077⟩
ACM Transactions on Parallel Computing, 2020, 7 (4), pp.1-25. ⟨10.1145/3418077⟩
ACM Transactions on Parallel Computing, Association for Computing Machinery, 2020, 7 (4), pp.1-25. ⟨10.1145/3418077⟩
ACM Transactions on Parallel Computing, 2020, 7 (4), pp.1-25. ⟨10.1145/3418077⟩
The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory cores before
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87bb3f1c2c23407ae66134f365943863
https://hal.inria.fr/hal-02991204/file/emuapps.pdf
https://hal.inria.fr/hal-02991204/file/emuapps.pdf
Nonnegative matrix factorization (NMF) is a prominent technique for data dimensionality reduction that has been widely used for text mining, computer vision, pattern discovery, and bioinformatics. In this paper, a framework called ARkNLS (Alternating
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd0b394bcd6d914a914e89822ca06b40
http://arxiv.org/abs/2007.06118
http://arxiv.org/abs/2007.06118
Publikováno v:
FTXS@SC
For the problem of computing the connected components of a graph, this paper considers the design of algorithms that are resilient to transient hardware faults, like bit flips. More specifically, it applies the technique of \emph{self-stabilization}.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e4e6c051935d289e0ae79282beb342a
https://doi.org/10.1109/ftxs49593.2019.00011
https://doi.org/10.1109/ftxs49593.2019.00011
Autor:
Jeffrey Young, Jiajia Li, Richard Vuduc, Eric R. Hein, Jason Riedy, Patrick Lavin, Srinivas Eswar, Thomas M. Conte
Publikováno v:
IPDPS Workshops
The Emu Chick is a prototype system designed around the concept of migratory memory-side processing. Rather than transferring large amounts of data across power-hungry, high-latency interconnects, the Emu Chick moves lightweight thread contexts to ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9e3e25a06b2902a44b7c0108ca1559a
https://doi.org/10.1109/ipdpsw.2018.00097
https://doi.org/10.1109/ipdpsw.2018.00097
Autor:
Eric R. Hein, Thomas M. Conte, Patrick Lavin, Srinivas Eswar, Jason Riedy, Jeffrey Young, Richard Vuduc, Jiajia Li
The Emu Chick is a prototype system designed around the concept of migratory memory-side processing. Rather than transferring large amounts of data across power-hungry, high-latency interconnects, the Emu Chick moves lightweight thread contexts to ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b8414c8dc0b1b182dce05eed9f7db5b