Minimax lower bounds for function estimation on graphs

Alisa Kirichenko, Harry van Zanten

Research output: Contribution to JournalArticleAcademicpeer-review


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.

Original languageEnglish
Pages (from-to)651-666
Number of pages16
JournalElectronic Journal of Statistics
Issue number1
Publication statusPublished - 1 Jan 2018
Externally publishedYes


  • Function estimation on graphs
  • Minimax lower bounds


Dive into the research topics of 'Minimax lower bounds for function estimation on graphs'. Together they form a unique fingerprint.

Cite this