Sparse Recovery via Differential Inclusions
نویسندگان
چکیده
In this paper, we recover sparse signals from their noisy linear measurements by solving nonlinear differential inclusions, which we call Bregman ISS and Linearized Bregman ISS. We show that under proper conditions, there exists a bias-free and sign-consistent point on their solution paths, which corresponds to a signal that is the unbiased estimate of the true signal and whose entries have the same signs as those of the true signs. Therefore, their solution paths are regularization paths better than the LASSO regularization path, since the points on the latter path are biased. We also show how to efficiently compute their solution paths in both continuous and discretized settings: the full solution paths can be exactly computed piece by piece, and a discretization leads to Linearized Bregman iteration, which is faster and easy to parallelize. Theoretical guarantees such as signconsistency and minimax optimal l2-error bounds are established in both continuous and discrete settings for specific points on the paths. Early-stopping rules for identifying these points are given. The key treatment relies on the development of differential inequalities for differential inclusions and their discretizations.
منابع مشابه
THE FULL AVERAGING OF FUZZY DIFFERENTIAL INCLUSIONS
In this paper the substantiation of the method of full averaging for fuzzy differential inclusions is considered. These results generalize the results of [17, 20] for differential inclusions with Hukuhara derivative and of [18] for fuzzy differential equations.
متن کاملSampling of finite elements for sparse recovery in large scale 3D electrical impedance tomography.
This study proposes a method to improve performance of sparse recovery inverse solvers in 3D electrical impedance tomography (3D EIT), especially when the volume under study contains small-sized inclusions, e.g. 3D imaging of breast tumours. Initially, a quadratic regularized inverse solver is applied in a fast manner with a stopping threshold much greater than the optimum. Based on assuming a ...
متن کاملStochastic differential inclusions of semimonotone type in Hilbert spaces
In this paper, we study the existence of generalized solutions for the infinite dimensional nonlinear stochastic differential inclusions $dx(t) in F(t,x(t))dt +G(t,x(t))dW_t$ in which the multifunction $F$ is semimonotone and hemicontinuous and the operator-valued multifunction $G$ satisfies a Lipschitz condition. We define the It^{o} stochastic integral of operator set-valued stochastic pr...
متن کاملDifferential transformation method for solving fuzzy differential inclusions by fuzzy partitions
متن کامل
Local Differential Privacy for Physical Sensor Data and Sparse Recovery
In this work, we exploit the ill-posedness of linear inverse problems to design algorithms to release differentially private data or measurements of the physical system. We discuss the spectral requirements on a matrix such that only a small amount of noise is needed to achieve privacy and contrast this with the ill-conditionedness. We then instantiate our framework with several diffusion opera...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014