Fundamentals Of Statistical Signal Processing

By S. Kay. 2001

6,667 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

AFEC: Active Forgetting of Negative Transfer in Continual Learning (2021, neutral): “(14) to obtain the Laplace approximation of p ( θ | D trainA ) as: The variance represents the inverse of Fisher Information matrix (FIM) F A , which can be approximated from the ﬁrst order derivatives to avoid computing the Hessian matrix [11]: Taking Eqn.”
Multichannel Interference Mitigation Techniques in Radio Astronomy (2000, methodology): “It has a closedform expression (cf. (Kay 1998)): Qχ2 2M (2γ) = e−γ M−1 ∑ k=0 γk k!”
Models for MIMO propagation channels: a review (2002, background): “Assuming that the channel coefficients are zero mean complex Gaussian, the first and second order moments of the MIMO channel are enough to characterize the propagation channel [ 39 ].”
Optimal designs for space-time linear precoders and decoders (2002, methodology): “The that minimizes the whole MSE matrix is the same as the MMSE (Wiener) receiver [15], which is known to minimize the tr MSE and is given by”
Identification of multiple leaks in pipeline: Linearized model, maximum likelihood, and super-resolution localization (2018, background): “More specifically, the estimates converge in probability to the actual leak positions and sizes and the variance of each estimator achieves the CRLB when the sample size tends to infinity [38].”
Geometry of quantum phase transitions (2019, methodology): “n the single parameter case, and in the multi-parameter one, the CR bound can be attained in the asymptotic limit of an inﬁnite number of experiment repetitions using the maximum likelihood estimator [333]. However, an interesting dierence between single and multi-parameter metrology arises due to c”
User-Centric Cell-Free Massive MIMO Networks: A Survey of Opportunities, Challenges and Solutions (2021, background): “…Lindeberg-Levy central limit theorem, the term 1 The implication is that if the vectors u and v are the serving channels for any two users, where N would be the number of serving antennas, and N is large, we can assume that these channels are orthogonal, which will cancel inter-user interference.”
Singular vector and singular subspace distribution for the matrix denoising model (2018, background): “1) appears prominently in the study of signal processing [40, 53], machine learning [69, 71] and statistics [17, 18, 27, 32].”
Adaptive blind signal and image processing (2002, background): “The above results can be summarized in the form of the following well known Gauss-Markov Theorem [689]: Theorem 2.”
DOA estimation using one-bit quantized measurements (2002, methodology): “The CRB is the lower bound on estimation variance of the vector parameters A for any unbiased estimator that satisfies certain regularity conditions (see e.g., [ 13 ])”