Zobrazeno 1 - 10
of 318
pro vyhledávání: '"PINGALI, KESHAV"'
Autor:
Maczuga, Paweł, Sikora, Maciej, Skoczeń, Maciej, Rożnawski, Przemysław, Tłuszcz, Filip, Szubert, Marcin, Łoś, Marcin, Dzwinel, Witold, Pingali, Keshav, Paszyński, Maciej
We present an open-source Physics Informed Neural Network environment for simulations of transient phenomena on two-dimensional rectangular domains, with the following features: (1) it is compatible with Google Colab which allows automatic execution
Externí odkaz:
http://arxiv.org/abs/2310.03755
Autor:
Pei, Yan, Pingali, Keshav
Many applications in important problem domains such as machine learning and computer vision are streaming applications that take a sequence of inputs over time. It is challenging to find knob settings that optimize the run-time performance of such ap
Externí odkaz:
http://arxiv.org/abs/2108.10701
Autor:
Hoang, Loc, Agarwal, Udit, Gill, Gurbinder, Dathathri, Roshan, Seal, Abhik, Martin, Brian, Pingali, Keshav
Graph transformer networks (GTN) are a variant of graph convolutional networks (GCN) that are targeted to heterogeneous graphs in which nodes and edges have associated type information that can be exploited to improve inference accuracy. GTNs learn i
Externí odkaz:
http://arxiv.org/abs/2106.08500
Numerical solutions to the Eikonal equation are computed using variants of the fast marching method, the fast sweeping method, and the fast iterative method. In this paper, we provide a unified view of these algorithms that highlights their similarit
Externí odkaz:
http://arxiv.org/abs/2103.05694
Many problems such as node classification and link prediction in network data can be solved using graph embeddings. However, it is difficult to use graphs to capture non-binary relations such as communities of nodes. These kinds of complex relations
Externí odkaz:
http://arxiv.org/abs/2103.09660
Hypergraph partitioning is used in many problem domains including VLSI design, linear algebra, Boolean satisfiability, and data mining. Most versions of this problem are NP-complete or NP-hard, so practical hypergraph partitioners generate approximat
Externí odkaz:
http://arxiv.org/abs/2012.13618
Graph pattern mining (GPM) is used in diverse application areas including social network analysis, bioinformatics, and chemical engineering. Existing GPM frameworks either provide high-level interfaces for productivity at the cost of expressiveness o
Externí odkaz:
http://arxiv.org/abs/2011.03135
Betweenness centrality (BC) is an important graph analytical application for large-scale graphs. While there are many efforts for parallelizing betweenness centrality algorithms on multi-core CPUs and many-core GPUs, in this work, we propose a novel
Externí odkaz:
http://arxiv.org/abs/2008.05718
Autor:
Łoś, Marcin, Woźniak, Maciej, Pingali, Keshav, Castillo, Luis Emilio Garcia, Alvarez-Aramberri, Julen, Pardo, David, Paszyński, Maciej
Publikováno v:
In Computers and Mathematics with Applications 1 December 2023 151:36-49
Supermodeling is a modern, model-ensembling paradigm that integrates several self-synchronized imperfect sub-models by controlling a few meta-parameters to generate more accurate predictions of complex systems' dynamics. Continual synchronization bet
Externí odkaz:
http://arxiv.org/abs/1912.12836