STOCHASTIC GRADIENT ALGORITHM BASED ON THE AVERAGE AGGREGATE FUNCTIONS

Abstract

The paper proposes a new scheme for the gradient solution to minimize losses averaged problem. It is an analog circuit used in the SAG algorithm in the case when the risk is calculated using the arithmetic mean. An illustrative example of the construction of robust classification based on the maximization of the surrogate median indentation.

Authors and Affiliations

Zaur Shibzukhov, Muhamed Kazakov

Keywords

Related Articles

MODEL FOR UNSTEADY OF DIFFUSION –ADVECTION OF RADON IN SOIL – ATMOSPHERE

We consider a mathematical model for unsteady transport of radon from the constant coefficients in the soil – atmosphere. An explicit analytical solution for this model and built at different times of his profiles.

GLOBAL MARKET FORECAST NANOPOWDERS

We have made a global analysis of the market nanopowders. Based on the available data it can be concluded that the introduction of nano-powders in various spheres of high technologies will occur every year more intensive...

ON SOLVABILITY OF THE BOUNDARY VALUE PROBLEM FOR ONE EVEN-ORDER EQUATION

In this paper boundary-value problem for one even-order equation is studied. The unique solvability of the problem is restored by additional conditions and conditions to domain.

NONLOCAL MODEL OF NEOCLASSICAL ECONOMIC GROWTH SOLOW

In generalization of the Solow model, when the change in resources in the production function described derivatives of fractional order in the sense of the Gerasimov – Caputo. As a result, we come to an important economi...

SAVE THE THIRD ADIABATIC INVARIANTS OF MOTION IN THE EQUATORIAL PLANE MAGNETIC FIELD WITH A WEAK AXIAL ASYMMETRY

The question of preservation of the third adiabatic invariant motion of charged particles vII = 0 (equatorial plane) in the flow and the canonical form in magnetic fields having a weak asymmetry. Go to rotating with the...

Download PDF file
  • EP ID EP487801
  • DOI 10.18454/2079-6641-2016-16-4-1-112-125
  • Views 132
  • Downloads 0

How To Cite

Zaur Shibzukhov, Muhamed Kazakov (2016). STOCHASTIC GRADIENT ALGORITHM BASED ON THE AVERAGE AGGREGATE FUNCTIONS. Вестник КРАУНЦ. Физико-математические науки, 4(), 112-125. https://europub.co.uk/articles/-A-487801