N
Nima Reyhani
Researcher at Aalto University
Publications - 33
Citations - 663
Nima Reyhani is an academic researcher from Aalto University. The author has contributed to research in topics: Kernel method & Kernel embedding of distributions. The author has an hindex of 10, co-authored 33 publications receiving 589 citations. Previous affiliations of Nima Reyhani include Airbnb & Trinity College, Dublin.
Papers
More filters
Journal ArticleDOI
Methodology for long-term prediction of time series
TL;DR: A global input selection strategy that combines forward selection, backward elimination (or pruning) and forward-backward selection is introduced and is used to optimize the three input selection criteria (k-NN, MI and NNE).
Book ChapterDOI
Direct and recursive prediction of time series using mutual information selection
TL;DR: This paper presents a comparison between direct and recursive prediction strategies and shows the superiority of the direct prediction strategy on the Poland electricity load benchmark.
Book ChapterDOI
LS-SVM hyperparameter selection with a nonparametric noise estimator
TL;DR: This method transforms the double optimization problem into a single optimization one and is tested on 2 problems: a toy example and the Pumadyn regression Benchmark.
Book ChapterDOI
Input and structure selection for k -NN approximator
TL;DR: This paper presents k-NN as an approximator for time series prediction problems, and it is shown that both Bootstraps and Leave-one-out provide a good estimate of the number of neighbors, k, where Leave- one-out fails.
Proceedings ArticleDOI
Almost Optimal Stochastic Weighted Matching with Few Queries
Soheil Behnezhad,Nima Reyhani +1 more
TL;DR: In this paper, the authors considered the stochastic matching problem and showed that for any arbitrarily small e > 0, one can get arbitrarily close to the optimum solution by querying only a constant number of edges per vertex.