Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/0069F4A3-9C49-47B7-A69D-11B96FBD36EA | - |
| Identifier | https://doi.org/10.26233/heallink.tuc.83411 | - |
| Language | en | - |
| Extent | 57 pages | el |
| Title | Parallel optimization algorithms for very large tensor decompositions | en |
| Title | Παράλληλοι αλγόριθμοι βελτιστοποίησης για παραγοντοποιήσεις πολύ μεγάλων τανυστών | el |
| Creator | Papagiannakos Ioannis-Marios | en |
| Creator | Παπαγιαννακος Ιωαννης-Μαριος | el |
| Contributor [Thesis Supervisor] | Liavas Athanasios | en |
| Contributor [Thesis Supervisor] | Λιαβας Αθανασιος | el |
| Contributor [Committee Member] | Karystinos Georgios | en |
| Contributor [Committee Member] | Καρυστινος Γεωργιος | el |
| Contributor [Committee Member] | Samoladas Vasilis | en |
| Contributor [Committee Member] | Σαμολαδας Βασιλης | el |
| Publisher | Πολυτεχνείο Κρήτης | el |
| Publisher | Technical University of Crete | en |
| Academic Unit | Technical University of Crete::School of Electrical and Computer Engineering | en |
| Academic Unit | Πολυτεχνείο Κρήτης::Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών | el |
| Content Summary | Tensors are generalizations of matrices to higher dimensions and are very powerful tools that can model a wide variety of multi-way data dependencies. As a result, tensor decompositions can extract useful information out of multi-aspect data tensors and have witnessed increasing popularity in various fields, such as data mining, social network analysis, biomedical applications, machine learning etc. Many decompositions have been proposed, but in this thesis we focus on Tensor Rank Decomposition or Canonical Polyadic Decomposition (CPD) using Alternating Least Squares (ALS). The main goal of the CPD is to decompose tensors into a sum of rank-1 terms, a procedure more difficult than its matrix counterpart, especially for large-scale tensors. CP decomposition via ALS consists of computationally expensive operations which cause performance bottlenecks. In order to accelerate this method and overcome these obstacles, we developed two parallel versions of the ALS that implement the CPD. The first one uses the full tensor and runs in parallel on heterogeneous & shared memory systems (CPUs and GPUs). The second one decomposes the tensor in parallel using small random block samples and runs on homogeneous & shared memory systems (CPUs). | en |
| Type of Item | Διπλωματική Εργασία | el |
| Type of Item | Diploma Work | en |
| License | http://creativecommons.org/licenses/by/4.0/ | en |
| Date of Item | 2019-10-04 | - |
| Date of Publication | 2019 | - |
| Subject | Canonical polyadic decomposition | en |
| Subject | Alternating least squares | en |
| Subject | shared memory systems | en |
| Subject | OpenMP | en |
| Subject | CUDA | en |
| Subject | Tensor | en |
| Subject | Randomized block sampling | en |
| Subject | PARAFAC | en |
| Subject | Parallel computing | en |
| Bibliographic Citation | Ioannis-Marios Papagiannakos, "Parallel optimization algorithms for very large tensor decompositions", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2019 | en |
| Bibliographic Citation | Ιωάννης-Μάριος Παπαγιαννάκος, "Παράλληλοι αλγόριθμοι βελτιστοποίησης για παραγοντοποιήσεις πολύ μεγάλων τανυστών", Διπλωματική Εργασία, Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, Πολυτεχνείο Κρήτης, Χανιά, Ελλάς, 2019 | el |
Copyright © DIAS 2013
