We derive real{time global optimizationmethods for several clustering optimization problems used in unsupervised texture segmentation. Speed is achieved by exploiting the topological relation of features to design a multiscale optimization technique, while accuracy and global optimization properties are gained using a deterministic annealing method. Coarse grained cost functions are derived for...

We derive real{time global optimizationmethods for several clustering optimization problems used in unsupervised texture segmentation. Speed is achieved by exploiting the topological relation of features to design a multiscale optimization technique, while accuracy and global optimization properties are gained using a deterministic annealing method. Coarse grained cost functions are derived for...

Sparse matrix-vector multiplication is an important computational kernel that performs poorly on most modern processors due to a low compute-to-memory ratio and irregular memory access patterns. Optimization is difficult because of the complexity of cache-based memory systems and because performance is highly dependent on the nonzero structure of the matrix. The Sparsity system is designed to a...

Abstract: Over the past years, there are increasing interests in recovering the signals from undersampling data where such signals are sparse under some orthogonal dictionary or tight framework, which is referred to be sparse synthetic model. More recently, its counterpart, i.e., the sparse analysis model, has also attracted researcher’s attentions where many practical signals which are sparse ...

The low utilization of SIMD units and memory bandwidth is the main performance bottleneck on SIMD processors for sparse matrix-vector multiplication (SpMV), which is one of the most important kernels in many scientific and engineering applications. This paper proposes a hybrid optimization method to break the performance bottleneck of SpMV on SIMD processors. The method includes a new sparse ma...

The idea behind Compressive Sensing(CS) is the reconstruction of sparse signals from very few samples, by means of solving a convex optimization problem. In this paper we propose a compressive sensing framework using the Two-Step Iterative Shrinkage/ Thresholding Algorithms(TwIST) for reconstructing speech signals. Further, we compare this framework with two other convex optimization algorithms...

This paper proposes a convex relaxation of a sparse support vector machine (SVM) based on the perspective relaxation of mixed-integer nonlinear programs. We seek to minimize the zero-norm of the hyperplane normal vector with a standard SVM hinge-loss penalty and extend our approach to a zeroone loss penalty. The relaxation that we propose is a second-order cone formulation that can be efficient...

In our ICML paper titled “On optimization methods for deep learning”, we discussed the standard and sparse autoencoder model. However, due to space limitations in our paper, we were not able to present further details about the bases learned by the sparse autoencoder model, compare the standard autoencoder with the Hessian Free approach as described in (Martens, 2010) and analyze in detail the ...

Optimizing the acquisition matrix is useful for compressed sensing of signals that are sparse in overcomplete dictionaries, because the acquisition matrix can be adapted to the particular correlations of the dictionary atoms. In this paper a novel formulation of the optimization problem is proposed, in the form of a rank-constrained nearest correlation matrix problem. Furthermore, improvements ...

In this paper novel CNN based multiuser detection algorithms are proposed which can provide high performance mobile communication. Multiuser detection in CDMA system come down to quadratic optimization. CNNs are capable of fast quadratic optimization when the quadratic form arising from the detection problem is generated by a sparse matrix. Since multiuser communication under heavy loaded scena...