Hiromi Yuya | Searcharxiv

arXiv2009

A gradient system on the quantum information space realizing the averaged learning equation of Hebb type

The averaged learning equation (ALEH) applicable to the principal component analyzer is studied from both quantum information geometry and dynamical system viewpoints. On the quantum information space (QIS), the space of regular density matrices endowed with the quantum SLD-Fisher metric, a gradient system is given as an extension of the ALEH; on the submanifold, consisting of the diagonal matrices, of the QIS, the gradient flow coincides with the ALEH up to a local diffeomorphism.

math.DS↗

arXiv2008

A gradient system on the quantum information space that realizes the Karmarkar flow for linear programming

In the paper of Uwano [Czech. J. of Phys., vol.56, pp.1311-1316 (2006)], a gradient system is found on the space of density matrices endowed with the quantum SLD Fisher metric (to be referred to as the quantum information space) that realizes a generalization of a gradient system on the space of multinomial distributions studied by Nakamura [Japan J. Indust. Appl. Math., vol.10, pp.179-189 (1993)]. On motived by those papers, the present paper aims to construct a gradient system on the quantum information space that realizes the Karmarkar flow, the continuous limit of the Karmarkar projective scaling algorithm for linear programming.

math.DS↗