arXiv subjects

Ozgur Yilmaz

Publications and source records attributed to Ozgur Yilmaz.

25 records · Page 2Linked to original sources

arXiv2014

Reservoir Computing using Cellular Automata

We introduce a novel framework of reservoir computing. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is capable of long short-term memory and it requires orders of magnitude less computation compared to Echo State Networks. Also, for additive cellular automaton rules, reservoir features can be combined using Boolean operations, which provides a direct way for concept building and symbolic processing, and it is much more efficient compared to state-of-the-art approaches.

cs.NE↗

arXiv2013

Non-Convex Compressed Sensing Using Partial Support Information

In this paper we address the recovery conditions of weighted $\ell_p$ minimization for signal reconstruction from compressed sensing measurements when partial support information is available. We show that weighted $\ell_p$ minimization with $0<p<1$ is stable and robust under weaker sufficient conditions compared to weighted $\ell_1$ minimization. Moreover, the sufficient recovery conditions of weighted $\ell_p$ are weaker than those of regular $\ell_p$ minimization if at least $50%$ of the support estimate is accurate. We also review some algorithms which exist to solve the non-convex $\ell_p$ problem and illustrate our results with numerical experiments.

cs.IT↗

arXiv2013

A fast randomized Kaczmarz algorithm for sparse solutions of consistent linear systems

The Kaczmarz algorithm is a popular solver for overdetermined linear systems due to its simplicity and speed. In this paper, we propose a modification that speeds up the convergence of the randomized Kaczmarz algorithm for systems of linear equations with sparse solutions. The speedup is achieved by projecting every iterate onto a weighted row of the linear system while maintaining the random row selection criteria of Strohmer and Vershynin. The weights are chosen to attenuate the contribution of row elements that lie outside of the estimated support of the sparse solution. While the Kaczmarz algorithm and its variants can only find solutions to overdetermined linear systems, our algorithm surprisingly succeeds in finding sparse solutions to underdetermined linear systems as well. We present empirical studies which demonstrate the acceleration in convergence to the sparse solution using this modified approach in the overdetermined case. We also demonstrate the sparse recovery capabilities of our approach in the underdetermined case and compare the performance with that of $\ell_1$ minimization.

math.NA↗

arXiv2012

Weighted-{$\ell_1$} minimization with multiple weighting sets

In this paper, we study the support recovery conditions of weighted $\ell_1$ minimization for signal reconstruction from compressed sensing measurements when multiple support estimate sets with different accuracy are available. We identify a class of signals for which the recovered vector from $\ell_1$ minimization provides an accurate support estimate. We then derive stability and robustness guarantees for the weighted $\ell_1$ minimization problem with more than one support estimate. We show that applying a smaller weight to support estimate that enjoy higher accuracy improves the recovery conditions compared with the case of a single support estimate and the case with standard, i.e., non-weighted, $\ell_1$ minimization. Our theoretical results are supported by numerical simulations on synthetic signals and real audio signals.

cs.IT↗

arXiv2012

Support driven reweighted $\ell_1$ minimization

In this paper, we propose a support driven reweighted $\ell_1$ minimization algorithm (SDRL1) that solves a sequence of weighted $\ell_1$ problems and relies on the support estimate accuracy. Our SDRL1 algorithm is related to the IRL1 algorithm proposed by Cand{è}s, Wakin, and Boyd. We demonstrate that it is sufficient to find support estimates with \emph{good} accuracy and apply constant weights instead of using the inverse coefficient magnitudes to achieve gains similar to those of IRL1. We then prove that given a support estimate with sufficient accuracy, if the signal decays according to a specific rate, the solution to the weighted $\ell_1$ minimization problem results in a support estimate with higher accuracy than the initial estimate. We also show that under certain conditions, it is possible to achieve higher estimate accuracy when the intersection of support estimates is considered. We demonstrate the performance of SDRL1 through numerical simulations and compare it with that of IRL1 and standard $\ell_1$ minimization.

cs.IT↗

arXiv2011

Recovering Compressively Sampled Signals Using Partial Support Information

In this paper we study recovery conditions of weighted $\ell_1$ minimization for signal reconstruction from compressed sensing measurements when partial support information is available. We show that if at least 50% of the (partial) support information is accurate, then weighted $\ell_1$ minimization is stable and robust under weaker conditions than the analogous conditions for standard $\ell_1$ minimization. Moreover, weighted $\ell_1$ minimization provides better bounds on the reconstruction error in terms of the measurement noise and the compressibility of the signal to be recovered. We illustrate our results with extensive numerical experiments on synthetic data and real audio and video signals.

cs.IT↗

arXiv2009

Sparse Recovery by Non-convex Optimization -- Instance Optimality

In this note, we address the theoretical properties of $Δ_p$, a class of compressed sensing decoders that rely on $\ell^p$ minimization with 0<p<1 to recover estimates of sparse and compressible signals from incomplete and inaccurate measurements. In particular, we extend the results of Candes, Romberg and Tao, and Wojtaszczyk regarding the decoder $Δ_1$, based on $\ell^1$ minimization, to $Δ_p$ with 0<p<1. Our results are two-fold. First, we show that under certain sufficient conditions that are weaker than the analogous sufficient conditions for $Δ_1$ the decoders $Δ_p$ are robust to noise and stable in the sense that they are (2,p) instance optimal for a large class of encoders. Second, we extend the results of Wojtaszczyk to show that, like $Δ_1$, the decoders $Δ_p$ are (2,2) instance optimal in probability provided the measurement matrix is drawn from an appropriate distribution.

cs.IT↗