What is the time complexity of spectral clustering and why (mathematically speaking) is it so?
What are possible existing alternatives to speed up the computations required by the algorithm?
Best Answer
Spectral Clustering is a clustering method that uses the spectrum (eigenvalues) of the similarity matrix of the data to perform dimensionality reduction before clustering the data in fewer dimensions.
It is a flexible class of clustering algorithms that can produce high-quality clusterings on small data sets, but which has limited applicability to largescale problems due to its computational complexity of O(n^3).
You can check the link below where a general framework for fast approximate spectral clustering is described.
Fast Approximate Spectral Clustering
Also at the second link below, a kernel based approach is decribed.
Similar Posts:
- Solved – the time complexity of spectral clustering and why is it so
- Solved – the time complexity of spectral clustering and why is it so
- Solved – Computational Complexity of Prediction using SVM and NN
- Solved – Clustering given pairwise distances with unknown cluster number
- Solved – When should I use k-means instead of Spectral Clustering