Corpus ID: 15610215

Compressed Learning : Universal Sparse Dimensionality Reduction and Learning in the Measurement Domain

@inproceedings{Calderbank2009CompressedL,
  title={Compressed Learning : Universal Sparse Dimensionality Reduction and Learning in the Measurement Domain},
  author={R. Calderbank},
  year={2009}
}
In this paper, we provide theoretical results to show that compressed learning , learning directly in the compressed domain, is possible. In Particular, we provide tight bounds demonstrating that the linear kernel SVM’s classifier in the measurement domain, with high probability, has true accuracy close to the accuracy of the best linear threshold classifier in the data domain. We show that this is beneficial both from the compressed sensing and the machine learning points of view. Furthermore… Expand
144 Citations

Figures and Tables from this paper

Generalization Error Analysis of Quantized Compressive Learning
  • 3
  • PDF
2D compressed learning: support matrix machine with bilinear random projections
  • Highly Influenced
  • PDF
From Affine Rank Minimization Solution to Sparse Modeling
  • 2
  • Highly Influenced
  • PDF
There and Back Again: A General Approach to Learning Sparse Models
  • 1
  • PDF
Finding needles in compressed haystacks
  • A. Calderbank, Sina Jafarpour
  • Computer Science
  • 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2012
  • 15
  • PDF
Compressed classification learning with Markov chain samples
  • Highly Influenced
Invertible Nonlinear Dimensionality Reduction via Joint Dictionary Learning
  • 4
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
Random Projections for Manifold Learning
  • 134
  • PDF
Random Projections of Smooth Manifolds
  • 391
  • Highly Influential
  • PDF
Combinatorial Algorithms for Compressed Sensing
  • 107
  • PDF
The restricted isometry property and its implications for compressed sensing
  • 3,219
  • PDF
Compressed sensing
  • D. Donoho
  • Computer Science
  • IEEE Transactions on Information Theory
  • 2006
  • 11,190
  • PDF
Construction of a Large Class of Deterministic Sensing Matrices That Satisfy a Statistical Isometry Property
  • 264
  • PDF
Compressed Video Sensing
  • 12
Sparse representations for image classification: learning discriminative and reconstructive non-parametric dictionaries
  • 140
  • PDF
Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
  • E. Candès, T. Tao
  • Mathematics, Computer Science
  • IEEE Transactions on Information Theory
  • 2006
  • 6,193
  • Highly Influential
  • PDF
A Generalized Restricted Isometry Property
  • 27
  • PDF
...
1
2
3
4
...