M
Mehrdad Mahdavi
Researcher at Pennsylvania State University
Publications - 97
Citations - 6508
Mehrdad Mahdavi is an academic researcher from Pennsylvania State University. The author has contributed to research in topics: Optimization problem & Computer science. The author has an hindex of 31, co-authored 88 publications receiving 5413 citations. Previous affiliations of Mehrdad Mahdavi include Michigan State University & Sharif University of Technology.
Papers
More filters
Journal ArticleDOI
An improved harmony search algorithm for solving optimization problems
TL;DR: The impacts of constant parameters on harmony search algorithm are discussed and a strategy for tuning these parameters is presented and the proposed algorithm can find better solutions when compared to HS and other heuristic or deterministic methods.
Journal ArticleDOI
Global-best harmony search
TL;DR: A new variant of HS, called global-best harmony search (GHS), is proposed in this paper where concepts from swarm intelligence are borrowed to enhance the performance of HS.
Proceedings Article
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison
TL;DR: It is shown that when there is a large gap in the eigen-spectrum of the kernel matrix, approaches based on the Nystrom method can yield impressively better generalization error bound than random Fourier features based approach.
Journal ArticleDOI
Hybridizing harmony search algorithm with sequential quadratic programming for engineering optimization problems
TL;DR: In this paper, a hybrid harmony search algorithm (HHSA) is proposed to solve engineering optimization problems with continuous design variables, where sequential quadratic programming (SQP) is employed to speed up local search and improve precision of the HSA solutions.
Journal Article
Adaptive Personalized Federated Learning
TL;DR: Information theoretically, it is proved that the mixture of local and global models can reduce the generalization error and a communication-reduced bilevel optimization method is proposed, which reduces the communication rounds to $O(\sqrt{T})$ and can achieve a convergence rate of $O(1/T)$ with some residual error.