Corrections to 'Gradient algorithms for designing predictive vector quantizers'

Abstract

An error in a paper by Chang and Gray (see ibid., vol.34, no.4, pp. 679-90, 1986) is pointed out and corrected. The error invalidates their observation that the generalized Lloyd algorithm is a gradient descent technique but the generalized Lloyd algorithm is a member of the related class of coordinate descent techniques. Convergence rate analysis of gradient descent algorithms for vector quantizer design is provided.