Skip to Main content Skip to Navigation
Journal articles

Adaptive confidence sets for matrix completion

Abstract : In the present paper we study the problem of existence of honest and adaptive confidence sets for matrix completion. We consider two statistical models: the trace regression model and the Bernoulli model. In the trace regression model, we show that honest confidence sets that adapt to the unknown rank of the matrix exist even when the error variance is unknown. Contrary to this, we prove that in the Bernoulli model, honest and adaptive confidence sets exist only when the error variance is known a priori. In the course of our proofs we obtain bounds for the minimax rates of certain composite hypothesis testing problems arising in low rank inference.
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01354030
Contributor : Olga Klopp <>
Submitted on : Friday, February 3, 2017 - 10:35:53 PM
Last modification on : Thursday, March 5, 2020 - 5:51:11 PM
Document(s) archivé(s) le : Friday, May 5, 2017 - 12:13:48 PM

Files

confmcversion2_hal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01354030, version 2
  • ARXIV : 1608.04861

Citation

Alexandra Carpentier, Olga Klopp, Matthias Löffler, Richard Nickl. Adaptive confidence sets for matrix completion. Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2018, 24 (4A), pp.2429 - 2460. ⟨hal-01354030v2⟩

Share

Metrics

Record views

655

Files downloads

359