Corpus ID: 6511163

Compressed Least-Squares Regression

@inproceedings{Maillard2009CompressedLR,
  title={Compressed Least-Squares Regression},
  author={O. Maillard and R. Munos},
  booktitle={NIPS},
  year={2009}
}

O. Maillard, R. Munos

Published in NIPS 2009

Computer Science, Mathematics

We consider the problem of learning, from K data, a regression function in a linear space of high dimension N using projections onto a random subspace of lower dimension M. From any algorithm minimizing the (possibly penalized) empirical risk, we provide bounds on the excess risk of the estimate computed in the projected subspace (compressed domain) in terms of the excess risk of the estimate built in the high-dimensional space (initial domain). We show that solving the problem in the… CONTINUE READING

View Paper

machinelearning.wustl.edu

Save to Library

Create Alert

Cite

Launch Research Feed