Exponential bounds implying construction of compressed sensing matrices, error-correcting codes, and neighborly polytopes by random sampling.
David L. DonohoJared TannerPublished in: IEEE Trans. Inf. Theory (2010)
Keyphrases
- random sampling
- compressed sensing
- random projections
- error correcting codes
- image reconstruction
- active learning
- sample size
- hyperparameters
- error correction
- upper bound
- natural images
- sliding window
- error correcting
- sparse representation
- lower bound
- singular value decomposition
- convex hull
- worst case
- machine learning
- original data
- data mining
- principal component analysis
- nearest neighbor
- support vector
- image processing