Corpus ID: 26909237

Compressive Statistical Learning with Random Feature Moments

@article{Gribonval2017CompressiveSL,
  title={Compressive Statistical Learning with Random Feature Moments},
  author={R. Gribonval and G. Blanchard and N. Keriven and Y. Traonmilin},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.07180}
}
  • R. Gribonval, G. Blanchard, +1 author Y. Traonmilin
  • Published 2017
  • Mathematics, Computer Science
  • ArXiv
  • We describe a general framework --compressive statistical learning-- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A near-minimizer of the risk is computed from the sketch through the solution of a nonlinear least squares problem. We investigate sufficient sketch sizes to control the… CONTINUE READING
    40 Citations
    Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling
    • 1
    • PDF
    Compressive Learning for Semi-Parametric Models
    • 1
    • Highly Influenced
    • PDF
    Quantized Compressive K-Means
    • 10
    • Highly Influenced
    • PDF
    Sketching for large-scale learning of mixture models
    • 48
    • PDF
    When compressive learning fails: blame the decoder or the sketch?
    • Highly Influenced
    • PDF
    Differentially Private Compressive K-means
    • 6
    • PDF
    Compressive Independent Component Analysis
    • 3
    • Highly Influenced
    Compressive Learning of Generative Networks
    • Highly Influenced
    • PDF
    Support Localization and the Fisher Metric for off-the-grid Sparse Regularization
    • 10
    • PDF
    A Dual Certificates Analysis of Compressive Off-the-Grid Recovery
    • 7

    References

    SHOWING 1-10 OF 105 REFERENCES
    Sketching for large-scale learning of mixture models
    • 48
    • PDF
    Compressive Gaussian Mixture estimation
    • 16
    • PDF
    New Analysis of Manifold Embeddings and Signal Recovery from Compressive Measurements
    • 56
    • PDF
    Toward Learning Gaussian Mixtures with Arbitrary Separation
    • 27
    Online Learning for Matrix Factorization and Sparse Coding
    • 2,336
    • PDF
    A spectral algorithm for learning mixture models
    • 190
    • PDF
    Compressive K-means
    • 31
    • PDF
    Learning mixtures of spherical gaussians: moment methods and spectral decompositions
    • 265
    • PDF
    Compressed sensing and best k-term approximation
    • 914
    • PDF