Minimax lower bounds for function estimation on graphs
From MaRDI portal
(Redirected from Publication:1746533)
Abstract: We study minimax lower bounds for function estimation problems on large graph when the target function is smoothly varying over the graph. We derive minimax rates in the context of regression and classification problems on graphs that satisfy an asymptotic shape assumption and with a smoothness condition on the target function, both formulated in terms of the graph Laplacian.
Recommendations
- Estimating a smooth function on a large graph by Bayesian Laplacian regularisation
- Low rank estimation of smooth kernels on graphs
- Lower bounds in estimation at a point under multi-index constraint
- Optimal Bayesian smoothing of functional observations over a large graph
- Low rank estimation of similarities on graphs
Cites work
- An introduction to the theory of graph spectra
- Estimating a smooth function on a large graph by Bayesian Laplacian regularisation
- Introduction to nonparametric estimation
- Kernels and regularization on graphs.
- Laplacian graph eigenvectors
- Learning Theory
- Nonparametric Bayesian label prediction on a graph
- On the effectiveness of Laplacian normalization for graph semi-supervised learning
- Statistical analysis of network data. Methods and models
- Uncertainty quantification in graph-based classification of high dimensional data
Cited in
(5)
This page was built for publication: Minimax lower bounds for function estimation on graphs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1746533)
