We consider a general class of convex optimization problems in which one seeks to minimize a strongly convex function over a closed and convex set which is by itself an optimal set of another convex problem. We introduce a gradient-based method, called the minimal norm gradient method, for solving this class of problems, and establish the convergence of the sequence generated by the algorithm a...

In this paper, we revisit three fundamental and popular stochastic optimization algorithms (namely, Online Proximal Gradient, Regularized Dual Averaging method and ADMM with online proximal gradient) and analyze their convergence speed under conditions weaker than those in literature. In particular, previous works showed that these algorithms converge at a rate of O(lnT/T ) when the loss functi...

In this paper, we study integral inequalities which will provide refinements of bounds unified operators established for convex and α , m -convex functions. A new definition function, namely, strongly id="M3"> function is applied in different forms ...

Although prox-regular functions in general are nonconvex, they possess properties that one would expect to find in convex or lowerC2  functions. The class of prox-regular functions covers all convex functions, lower C2  functions and strongly amenable functions. At first, these functions have been identified in finite dimension using proximal subdifferential. Then, the definition of prox-regula...

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve either optimal or near optimal utility bounds with less gradient complexity compared with previous work. For ERM with smooth convex loss function in high-dimensio...

In many machine learning problems such as the dual form of SVM, the objective function to be minimized is convex but not strongly convex. This fact causes difficulties in obtaining the complexity of some commonly used optimization algorithms. In this paper, we proved the global linear convergence on a wide range of algorithms when they are applied to some non-strongly convex problems. In partic...

In the present paper certain subclasses of strongly starlike and strongly convex functions defined by convolution with the generalized Hurwitz -Lerch Zeta function are investigated. Some inclusion relations are also mentioned as special cases of our main results.

In many machine learning problems such as the dual form of SVM, the objective function to be minimized is convex but not strongly convex. This fact causes difficulties in obtaining the complexity of some commonly used optimization algorithms. In this paper, we proved the global linear convergence on a wide range of algorithms when they are applied to some non-strongly convex problems. In partic...

The main aim of this paper is to give refinement bounds fractional integral operators involving extended generalized Mittag-Leffler functions. A new definition, namely, strongly α , m -convex function introduced obtain improvements fo...

In this paper, we propose a cubic regularized Newton method for solving the convex-concave minimax saddle point problems. At each iteration, subproblem is constructed and solved, which provides search direction iterate. With properly chosen stepsizes, shown to converge with global linear local superlinear convergence rates, if function gradient Lipschitz strongly-convex-strongly-concave. case t...