Analysis of Nyström method with sequential ridge leverage score sampling - Archive ouverte HAL Access content directly
Conference Papers Year :

Analysis of Nyström method with sequential ridge leverage score sampling

(1) , (1) , (1)
1
Daniele Calandriello
  • Function : Author
  • PersonId : 960706
Alessandro Lazaric
Michal Valko

Abstract

Large-scale kernel ridge regression (KRR) is limited by the need to store a large kernel matrix Kt. To avoid storing the entire matrix Kt, Nyström methods subsample a subset of columns of the kernel matrix, and efficiently find an approximate KRR solution on the reconstructed Kt . The chosen subsampling distribution in turn affects the statistical and computational tradeoffs. For KRR problems, [15, 1] show that a sampling distribution proportional to the ridge leverage scores (RLSs) provides strong reconstruction guarantees for Kt. While exact RLSs are as difficult to compute as a KRR solution, we may be able to approximate them well enough. In this paper, we study KRR problems in a sequential setting and introduce the INK-ESTIMATE algorithm, that incrementally computes the RLSs estimates. INK-ESTIMATE maintains a small sketch of Kt, that at each step is used to compute an intermediate estimate of the RLSs. First, our sketch update does not require access to previously seen columns, and therefore a single pass over the kernel matrix is sufficient. Second, the algorithm requires a fixed, small space budget to run dependent only on the effective dimension of the kernel matrix. Finally, our sketch provides strong approximation guarantees on the distance ∥Kt−Kt∥2 , and on the statistical risk of the approximate KRR solution at any time, because all our guarantees hold at any intermediate step.
Fichier principal
Vignette du fichier
calandriello2016analysis.pdf (428.03 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01343674 , version 1 (09-07-2016)

Identifiers

  • HAL Id : hal-01343674 , version 1

Cite

Daniele Calandriello, Alessandro Lazaric, Michal Valko. Analysis of Nyström method with sequential ridge leverage score sampling. Uncertainty in Artificial Intelligence, Jun 2016, New York City, United States. ⟨hal-01343674⟩
240 View
270 Download

Share

Gmail Facebook Twitter LinkedIn More