A number of nonlinear diffusion-like equations have been proposed for filtering noise, removing blurring and other applications. These equations are usually developed as time independent equations. An artificial time is introduced to change these equations to parabolic type equations which are then marched to a steady state. In practice the time iteration is stopped before the steady state is r...

The use of the expectation-maximization algorithm to obtain pseudo-maximum likelihood estimates (i.e. the EM-ML algorithm) of radiopharmaceutical distributions based on data collected from emission computed tomography (ECT) systems is now a well developed area, as witnessed by a number of recent articles on that topic, including the detailed study of the relative performance of EM-ML and FBP re...

Detecting infeasibility in conic optimization and providing certificates for infeasibility pose a bigger challenge than in the linear case due to the lack of strong duality. In this paper we generalize the approximate Farkas lemma of Todd and Ye [12] from the linear to the general conic setting, and use it to propose stopping criteria for interior point algorithms using self-dual embedding. The...

This paper proposes the use of statistical criteria for early stopping Support Vector Machines, both for regression and classification problems. The method basically stops the minimization of the primal functional when moments of the error signal (up to forth order) become stationary, rather than according to a tolerance threshold of primal convergence itself. This simple strategy induces lower...

An iterative multiuser detection (IMUD) receiver is considered for a code-division multiple-access (CDMA) system with turbo codes. Fidelity is considered as a metric for convergence analysis and an approximation of fidelity as a function of variance of the log-likelihood ratios is introduced. Fidelity charts are compared with extrinsic information transfer (EXIT) charts as tools for convergence...

This letter proposes an efficient and simple stopping criterion for turbo decoding, which is derived by observing the behavior of log-likelihood ratio (LLR) values. Based on the behavior, the proposed criterion counts the number of absolute LLR values less than a threshold and the number of hard decision 1’s in order to complete the iterative decoding procedure. Simulation results show that the...

We show that, when solving a linear system with an iterative method, it is necessary to measure the error in the space in which the residual lies. We present examples of linear systems which emanate from the finite element discretization of elliptic partial differential equations, and we show that, when we measure the residual in H−1( ), we obtain a true evaluation of the error in the solution,...

Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an approximation to the gradient of the data log-likelihood. A simple reconstruction error is often used to decide whether the approximation provided by the CD algorithm is good enoug...

NIR tomography image reconstruction can be improved by incorporating spectral constraints and prior spatial information. The convergence of scattering power was studied based on the distribution of projection error with different parameters. The reason that scattering properties are harder to recover than chromophore concentrations was discussed. Using “hard prior” spectral reconstruction, the ...

By default, the edge-consistent LPR is solved using Message Passing (MP) algorithm to initialize β until convergence or for at most 1000 iterations, whichever comes first. If the gap between the upper and lower bounds is not smaller than 10 (stopping criteria) already, we further apply our BB method or MPLP-CP method [4]. Both methods stop when the same stopping criteria (gap < 10) is reached. ...