Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Nuri Denizcan Vanli"'
Publikováno v:
Mathematical Programming. 195:243-281
Semidefinite programming (SDP) with diagonal constraints arise in many optimization problems, such as Max-Cut, community detection and group synchronization. Although SDPs can be solved to arbitrary precision in polynomial time, generic convex solver
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f11ca875daaddbfd1fc8fc2d803460c
https://doi.org/10.1007/s10107-021-01686-3
https://doi.org/10.1007/s10107-021-01686-3
Publikováno v:
Springer Berlin Heidelberg
We consider coordinate descent (CD) methods with exact line search on convex quadratic problems. Our main focus is to study the performance of the CD method that use random permutations in each epoch and compare it to the performance of the CD method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4273a0807cfa5e03929d1dd3d66094f
https://doi.org/10.1007/s10107-019-01438-4
https://doi.org/10.1007/s10107-019-01438-4
Publikováno v:
SIAM Journal on Optimization. 28:1282-1300
We focus on the problem of minimizing the sum of smooth component functions (where the sum is strongly convex) and a non-smooth convex function, which arises in regularized empirical risk minimization in machine learning and distributed constrained o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bec6fa19b48701c204a7f95322d5e9b3
https://doi.org/10.1137/16m1094415
https://doi.org/10.1137/16m1094415
Autor:
Jerónimo Arenas-García, Luis A. Azpicueta-Ruiz, Theodore W. Berger, Pantelis Bouboulis, Renato Candido, Alberto Carini, Stefania Cecchi, Badong Chen, Jie Chen, Symeon Chouvardas, Danilo Comminiello, Konstantinos Diamantaras, Georgios B. Giannakis, Christian Hofmann, Vassilis N. Ioannidis, Walter Kellermann, Bahare Kiumarsi, Suleyman Serdar Kozat, S.Y. Kung, Frank L. Lewis, Zhe Li, Derong Liu, Biao Luo, Meng Ma, Danilo P. Mandic, Tomas McKelvey, Hamidreza Modares, Athanasios N. Nikolakopoulos, Simone Orcioni, Raffaele Parisi, José C. Príncipe, Cédric Richard, Brian S. Robinson, Daniel Romero, Simone Scardapane, Michele Scarpiniti, Magno T.M. Silva, Dong Song, Sergios Theodoridis, Aurelio Uncini, Kyriakos G. Vamvoudakis, Nuri Denizcan Vanli, Xin Wang, Huai-Ning Wu, Yili Xia, Min Xiang, Yinan Yu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c20daf2f46fdc1880e594dc62f5ace45
https://doi.org/10.1016/b978-0-12-812976-0.00024-5
https://doi.org/10.1016/b978-0-12-812976-0.00024-5
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems
We study online nonlinear learning over distributed multiagent systems, where each agent employs a single hidden layer feedforward neural network (SLFN) structure to sequentially minimize arbitrary loss functions. In particular, each agent trains its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46e53c6d17772ed4b70430aea8ed00cc
https://pubmed.ncbi.nlm.nih.gov/26978837
https://pubmed.ncbi.nlm.nih.gov/26978837
Publikováno v:
Physical Communication
We investigate underwater acoustic (UWA) channel equalization and introduce hierarchical and adaptive nonlinear channel equalization algorithms that are highly efficient and provide significantly improved bit error rate (BER) performance. Due to the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e6cbd48ec5b0ad719ebd730e64d0962
Autor:
Suleyman S. Kozat, Nuri Denizcan Vanli
Publikováno v:
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Neural Networks and Learning Systems
Cataloged from PDF version of article. We study sequential prediction of real-valued, arbitrary, and unknown sequences under the squared error loss as well as the best parametric predictor out of a large, continuous class of predictors. Inspired by r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79182810d59c614915cf6886d02d3869
https://hdl.handle.net/11693/12843
https://hdl.handle.net/11693/12843