Sparse signal recovery with exponential-family noise

The problem of sparse signal recovery from a relatively small number of noisy measurements has been studied extensively in the recent literature on compressed sensing. However, the focus of those studies appears to be limited to the case of linear projections disturbed by Gaussian noise, and the sparse signal reconstruction problem is treated as linear regression with l1-norm regularization constraint. A natural question to ask is whether one can accurately recover sparse signals under different noise assumptions. Herein, we extend the results of [13] to the more general case of exponential-family noise that includes Gaussian noise as a particular case, and yields l1-regularized Generalized Linear Model (GLM) regression problem. We show that, under standard restricted isometry property (RIP) assumptions on the design matrix, l1-minimization can provide stable recovery of a sparse signal in presence of the exponential-family noise, provided that certain sufficient conditions on the noise distribution are satisfied.

[1]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[2]  Tom M. Mitchell,et al.  Learning to Decode Cognitive States from Brain Images , 2004, Machine Learning.

[3]  Alina Beygelzimer,et al.  Efficient Test Selection in Active Diagnosis via Entropy Approximation , 2005, UAI.

[4]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[5]  Emmanuel J. Candès,et al.  Decoding by linear programming , 2005, IEEE Transactions on Information Theory.

[6]  Sheng Ma,et al.  Adaptive diagnosis in distributed systems , 2005, IEEE Transactions on Neural Networks.

[7]  Inderjit S. Dhillon,et al.  Clustering with Bregman Divergences , 2005, J. Mach. Learn. Res..

[8]  Mee Young Park,et al.  L 1-regularization path algorithm for generalized linear models , 2006 .

[9]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

[10]  D. Donoho.  For most large underdetermined systems of equations, the minimal 𝓁1‐norm near‐solution approximates the sparsest near‐solution , 2006 .

[11]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[12]  E.J. Candes.  Compressive Sampling , 2022 .

[13]  Emmanuel J. Candès,et al.  Quantitative Robust Uncertainty Principles and Optimally Sparse Decompositions , 2004, Found. Comput. Math..

[14]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[15]  Mee Young Park,et al.  L1‐regularization path algorithm for generalized linear models , 2007 .

[16]  Irina Rish,et al.  Blind source separation approach to performance diagnosis and dependency discovery , 2007, IMC '07.

[17]  Jeffrey O. Kephart,et al.  Evaluation of Optimization Methods for Network Bottleneck Diagnosis , 2007, Fourth International Conference on Autonomic Computing (ICAC'07).

[18]  Martin J. Wainwright,et al.  A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers , 2009, NIPS.

[19]  A. Ravishankar Rao,et al.  Prediction and interpretation of distributed neural activity with sparse models , 2009, NeuroImage.