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
    102 Citations
    Fast Sparse Least-Squares Regression with Non-Asymptotic Guarantees
    • 2
    • PDF
    Compressed Least-Squares Regression on Sparse Spaces
    • 26
    • Highly Influenced
    • PDF
    Least-Squares Regression on Sparse Spaces
    • 1
    • PDF
    Compressed fisher linear discriminant analysis: classification of randomly projected data
    • 46
    • PDF
    Scrambled Objects for Least-Squares Regression
    • 2
    • PDF
    Asymptotics for Sketching in Least Squares
    • PDF
    Asymptotics for Sketching in Least Squares Regression
    • 25
    • PDF
    Sharp analysis of low-rank kernel matrix approximations
    • 204
    • PDF
    Linear regression with random projections
    • 38
    • PDF

    References

    SHOWING 1-10 OF 30 REFERENCES
    Risk bounds in linear regression through PAC-Bayesian truncation
    • 9
    • PDF
    Compressed Regression
    • 36
    • PDF
    On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization
    • 269
    • PDF
    Some sharp performance bounds for least squares regression with L1 regularization
    • 244
    • PDF
    Persistence in high-dimensional linear predictor selection and the virtue of overparametrization
    • 333
    • PDF
    Piecewise linear regularized solution paths
    • 454
    • PDF
    Signal recovery from random projections
    • 251
    • PDF
    Compressed sensing
    • D. Donoho
    • Computer Science
    • IEEE Transactions on Information Theory
    • 2006
    • 11,317
    • PDF
    Random Projection, Margins, Kernels, and Feature-Selection
    • 121
    • PDF