We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the non-smooth term. We show that both the basic proximal-gradient method and the accelerated proximal-gradient method achieve the s...

In this paper, we consider adaptive estimation of an unknown planar compact, convex set from noisy measurements of its support function. Both the problem of estimating the support function at a point and that of estimating the whole convex set are studied. For pointwise estimation, we consider the problem in a general non-asymptotic framework, which evaluates the performance of a procedure at e...

The problem of estimating the domain of attraction (DA) of equilibria of polynomial systems is considered. Specifically, the computation of the quadratic Lyapunov function which maximizes the volume of the estimate is addressed. In order to solve this double non-convex optimization problem, a semi-convex approach based on Linear Matrix Inequalities (LMIs) is proposed. Moreover, for the case of ...

<p style='text-indent:20px;'>In this work, we have proposed a new approach for solving the linear-quadratic optimal control problem, where quality criterion is quadratic function, which can be convex or non-convex. In approach, transform continuous problem into optimization using Cauchy discretization technique, then solve it with active-set method. order to study efficiency and accuracy ...

We present locally-linear learning machines (L3M) for multi-class classification. We formulate a global convex risk function to jointly learn linear feature space partitions and region-specific linear classifiers. L3M’s features such as: (1) discriminative power similar to Kernel SVMs and Adaboost; (2) tight control on generalization error; (3) low training time cost due to on-line training; (4...

Lemma A.1 (a) A real-valued convex function is also 0-convex and hence k-convex for all k ≥ 0. A k1-convex function is also a k2-convex function for k1 ≤ k2. (b) If f1(y) and f2(y) are k1-convex and k2-convex respectively, then for α, β ≥ 0, αf1(y) + βf2(y) is (αk1 + βk2)-convex. (c) If f(y) is k-convex and w is a random variable, then E{f(y − w)} is also k-convex, provided E{|f(y − w)|} < ∞ fo...