Searcharxiv⌕ Search

arXiv subjects

Cagatay Candan

Publications and source records attributed to Cagatay Candan.

3 recordsLinked to original sources

Delta-Iterations: A General-Purpose Linear Regression Solver for Huber's Penalty, $ε$-Insensitive Loss, and Other Moreau Envelope-Based Loss Functions

A general-purpose linear regression solver for a class of smooth loss functions is presented. The method applies to loss functions of the Moreau envelope type, which are continuously differentiable and have Lipschitz-continuous first derivatives. This class includes piecewise-defined cost functions consisting of constant, linear and quadratic segments, such as Huber's loss, insensitive least squares, one-sided least squares. The convergence guarantee provided by the associated proximal operator, the simplicity of the method and its versatility in handling various cost functions within a unified framework are its main advantages. MATLAB code for reproducing the numerical results presented in this article is provided.

eess.SP↗

Polynomial Order Selection for Savitzky-Golay Smoothers via N-fold Cross-Validation (extended version)

Savitzky-Golay (SG) smoothers are noise suppressing filters operating on the principle of projecting noisy input onto the subspace of polynomials. A poorly selected polynomial order results in over- or under-smoothing which shows as either bias or excessive noise at the output. In this study, we apply the N-fold cross-validation technique (also known as leave-one-out cross-validation) for model order selection and show that the inherent analytical structure of the SG filtering problem, mainly its minimum norm formulation, enables an efficient and effective order selection solution. More specifically, a novel connection between the total prediction error and SG-projection spaces is developed to reduce the implementation complexity of cross-validation method. The suggested solution compares favorably with the state-of-the-art Bayesian Information Criterion (BIC) rule in non-asymptotic signal-to-noise ratio (SNR) and sample size regimes. MATLAB codes reproducing the numerical results are provided.

eess.SP↗

An Automated Window Selection Procedure For DFT Based Detection Schemes To Reduce Windowing SNR Loss

The classical spectrum analysis methods utilize window functions to reduce the masking effect of a strong spectral component over weaker components. The main cost of side-lobe reduction is the reduction of signal-to-noise ratio (SNR) level of the output spectrum. We present a single snapshot method which optimizes the selection of most suitable window function among a finite set of candidate windows, say rectangle, Hamming, Blackman windows, for each spectral bin. The main goal is to utilize different window functions at each spectral output depending on the interference level encountered at that spectral bin so as to reduce the SNR loss associated with the windowing operation. Stated differently, the windows with strong interference suppression capabilities are utilized only when a sufficiently powerful interferer is corrupting the spectral bin of interest is present, i.e. only when this window is needed. The achieved reduction in the windowing SNR loss can be important for the detection of low SNR targets.

eess.SP↗