19 citations · 38 across the 6 of their papers we have counts for
6 papers
Impact of regularization on Spectral Clustering
Antony Joseph, Bin Yu
The performance of spectral clustering can be considerably improved via regularization, as demonstrated empirically in Amini et. al (2012). Here, we provide an attempt at quantifyi…
Fast Sparse Superposition Codes have Exponentially Small Error Probability for R < C
Antony Joseph, Andrew Barron
For the additive white Gaussian noise channel with average codeword power constraint, sparse superposition codes are developed. These codes are based on the statistical high-dimens…
Lossy Compression via Sparse Linear Regression: Performance under Minimum-distance Encoding
Ramji Venkataramanan, Antony Joseph, Sekhar Tatikonda
We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression. Cod…
Variable Selection in High Dimensions with Random Designs and Orthogonal Matching Pursuit
Antony Joseph
The performance of Orthogonal Matching Pursuit (OMP) for variable selection is analyzed for random designs. When contrasted with the deterministic case, since the performance is he…
Toward Fast Reliable Communication at Rates Near Capacity with Gaussian Noise
Andrew R Barron, Antony Joseph
For the additive Gaussian noise channel with average codeword power constraint, sparse superposition codes and adaptive successive decoding is developed. Codewords are linear combi…
Least Squares Superposition Codes of Moderate Dictionary Size, Reliable at Rates up to Capacity
Andrew R. Barron, Antony Joseph
For the additive white Gaussian noise channel with average codeword power constraint, new coding methods are devised in which the codewords are sparse superpositions, that is, line…