Limit theorems for out-of-sample extensions of the adjacency and Laplacian spectral embeddings.
Keith D. LevinFred RoostaMinh TangMichael W. MahoneyCarey E. PriebePublished in: J. Mach. Learn. Res. (2021)
Keyphrases
- limit theorems
- heavy traffic
- spectral decomposition
- confidence intervals
- queue length
- laplacian matrix
- steady state
- low dimensional
- spectral analysis
- vector space
- manifold learning
- dimensionality reduction
- graph laplacian
- high dimensional data
- asymptotically optimal
- queueing networks
- long run
- neural network
- spectral methods
- sufficient conditions
- euclidean space
- information systems