On the Achievability of Cramér-Rao Bound In Noisy Compressed Sensing
Recently, it has been proved in Babadi et al. that in noisy compressed sensing, a joint typical estimator can asymptotically achieve the Cramer-Rao lower bound of the problem.To prove this result, this paper used a lemma,which is provided in Akcakaya et al,that comprises the main building block of the proof. This lemma is based on the assumption of Gaussianity of the measurement matrix and its randomness in the domain of noise. In this correspondence, we generalize the results obtained in Babadi et al by dropping the Gaussianity assumption on the measurement matrix. In fact, by considering the measurement matrix as a deterministic matrix in our analysis, we find a theorem similar to the main theorem of Babadi et al for a family of randomly generated (but deterministic in the noise domain) measurement matrices that satisfy a generalized condition known as The Concentration of Measures Inequality. By this, we finally show that under our generalized assumptions, the Cramer-Rao bound of the estimation is achievable by using the typical estimator introduced in Babadi et al.
Code (0)
등록된 구현이 없습니다.
Tasks
compressed sensingLEMMASimilar Papers 제목 키워드 기반
Learning Structured Compressed Sensing with Automatic Resource Allocation
Multidimensional data acquisition often requires extensive time and poses significant challenges for hardware and software regarding data storage and processing. Rather than designing a single compression matrix as in co…
compressed sensingLower Bounds for Compressed Sensing with Generative Models
The goal of compressed sensing is to learn a structured signal $x$ from a limited number of noisy linear measurements $y \approx Ax$. In traditional compressed sensing, "structure" is represented by sparsity in some know…
2kcompressed sensingOn the Power of Compressed Sensing with Generative Models
The goal of compressed sensing is to learn a structured signal $x$ from a limited number of noisy linear measurements $y \approx Ax$. In traditional compressed sensing, ``structure'' is represented by sparsity in some k…
compressed sensingOn the Power of Compressed Sensing with Generative Models
The goal of compressed sensing is to learn a structured signal $x$ from a limited number of noisy linear measurements $y \approx Ax$. In traditional compressed sensing, ``structure'' is represented by sparsity in some k…
compressed sensingUncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework fo…
compressed sensingDimensionality ReductionRepresentation Learning