Information-Theoretic Limits on Sparsity Recovery in the High-Dimensional and Noisy Setting

IEEE TRANSACTIONS ON INFORMATION THEORY

卷 55, 期 12, 页码 5728-5741

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

Compressed sensing; l(1)-relaxation; Fano's method; high-dimensional statistical inference; information-theoretic bounds; Lasso; model selection; signal denoising; sparsity pattern; sparsity recovery; subset selection; support recovery

Computer Science, Information Systems Engineering, Electrical & Electronic

1. National Science Foundation [NSF DMS-0528488, CAREER-CCF0545862]
2. Microsoft Research Grant
3. Sloan Foundation Fellowship