We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate method, which alternates between maximizing over one (or more) randomly chosen dual variable and minimizing over the primal variab...

Although there exist plentiful theories of empirical risk minimization (ERM) for supervised learning, current theoretical understandings of ERM for a related problem—stochastic convex optimization (SCO), are limited. In this work, we strengthen the realm of ERM for SCO by exploiting smoothness and strong convexity conditions to improve the risk bounds. First, we establish an Õ(d/n+ √ F∗/n) risk...

The Green function for Klein-Gordon-Dirac equation is obtained. The case with the dominating Klein-Gordon term is considered. There seems to be a formal analogy between our problem and a certain problem for a 4-dimensional particle moving in the external field. The explicit relations between the wave function, Green function and initial conditions are established with the help of the T -exponen...

Uni6n M a t d t i c a Argentina Vol. 35 1990. Introduction The main purpose of this paper is to give a comprehensive motivation, with most of the key ideas used in the recent work by Garroni and Menaldi [lo], on the construction of the Green function G(z, t, (, r) for an integro-differential initial boundary value problem, when the differential operator is a second-order parabolic operator not ...

A mathematic model of Green function is build for two dimension free water surface. The analytic expression of Green function is obtained by introducing a parameter of complex number. The intrinsic properties of Green function are discussed for the special parameter values. The real and imaginary parts of H function are shown in the paper.

While research results exist in energy efficient hardware and its components to achieve environmental sustainability, major research is needed to relate energy consumption of hardware to energy consumption of its executing software. Since software is playing an increasing role in supporting our society its energy efficiency and environmental impact become more important. Green IT and green soft...

The single-particle nuclear potential is intrinsically nonlocal. In this paper, we consider nonlocalities which arise from the many-body and fermionic nature of the nucleus. We investigate the effects of nonlocality in the nuclear potential by developing the Green’s function for nonlocal potentials. The formal Green’s function integral is solved analytically in two different limits of the wavel...

A new method for the stabilization of the sign problem in the Green Function Monte Carlo technique is proposed. The method is devised for real lattice Hamiltonians and is based on an iterative ”stochastic reconfiguration” scheme which introduces some bias but allows a stable simulation with constant sign. The systematic reduction of this bias is in principle possible. The method is applied to t...