Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Maher Nouiehed"'
Autor:
Raed Kontar, Naichen Shi, Xubo Yue, Seokhyun Chung, Eunshin Byon, Mosharaf Chowdhury, Jionghua Jin, Wissam Kontar, Neda Masoud, Maher Nouiehed, Chinedum E. Okwudire, Garvesh Raskutti, Romesh Saigal, Karandeep Singh, Zhi-Sheng Ye
Publikováno v:
IEEE Access, Vol 9, Pp 156071-156113 (2021)
The Internet of Things (IoT) is on the verge of a major paradigm shift. In the IoT system of the future, IoFT, the “cloud” will be substituted by the “crowd” where model training is brought to the edge, allowing IoT devices to collaboratively
Externí odkaz:
https://doaj.org/article/062590f52ce0422fa225371fa898a329
In this paper, we propose GIFAIR-FL, a framework that imposes group and individual fairness (GIFAIR) to federated learning (FL) settings. By adding a regularization term, our algorithm penalizes the spread in the loss of client groups to drive the op
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a7e7fed6dd55a1ca29e8412808ec277
In an effort to improve generalization in deep learning and automate the process of learning rate scheduling, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers. Our method dynamically updates the le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a43a63fbd04e7f404a3955f7379248b
The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7f6a6dec08cef3023de5dc5dde3786a
Publikováno v:
Mathematical Programming. 174:195-222
With the increasing interest in applying the methodology of difference-of-convex (dc) optimization to diverse problems in engineering and statistics, this paper establishes the dc property of many functions in various areas of applications not previo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f11c2caa12e3fc7f7e24748b932a7a73
https://doi.org/10.1007/s10107-018-1286-0
https://doi.org/10.1007/s10107-018-1286-0
Autor:
Maher Nouiehed, Sheldon M. Ross
Publikováno v:
Journal of Applied Probability. 55:318-324
We consider the Bernoulli bandit problem where one of the arms has win probability α and the others β, with the identity of the α arm specified by initial probabilities. With u = max(α, β), v = min(α, β), call an arm with win probability u a g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84f48867726381ee5d4e0be5af9faee2
https://doi.org/10.1017/jpr.2018.19
https://doi.org/10.1017/jpr.2018.19
Autor:
Maher Nouiehed, Abbas Alhakim
Publikováno v:
Designs, Codes and Cryptography. 85:381-394
We give a one-step construction of de Bruijn sequences of general alphabet size and with order \(n+k\), given a de Bruijn sequence of order n and any integer \(k>1\). This is achieved by using an appropriate class of graph homomorphisms between de Br
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::776b4a7760d1f9f59e7ec6b409519607
https://doi.org/10.1007/s10623-016-0314-4
https://doi.org/10.1007/s10623-016-0314-4
Autor:
Meisam Razaviyayn, Maher Nouiehed
Motivated by TRACE algorithm [Curtis et al. 2017], we propose a trust region algorithm for finding second order stationary points of a linearly constrained non-convex optimization problem. We show the convergence of the proposed algorithm to (\epsilo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::694192542dbec664134a25e65c6760ab
Publikováno v:
Mathematical Programming. 174:223-224
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8600cb213f728f8acf740c168c09dd3
https://doi.org/10.1007/s10107-019-01378-z
https://doi.org/10.1007/s10107-019-01378-z
Publikováno v:
ACM Transactions on Knowledge Discovery from Data; Sep2024, Vol. 18 Issue 8, p1-13, 13p