| Learning Decentralized Goal-based Vector Quantization (2007) | |||||||||||||||
Abstract | |||||||||||||||
| In this paper we consider the following generalization of classical vector quantization: to (vector) quantize or, equivalently, to partition the domain of a given function such that each cell in the partition satisfies a given set of topological constraints. We call this formulation as Decentralized Goal-based Vector Quantization (DGVQ). The formulation is motivated by the resource allocation mechanism design problem in Economics. A Kohonen-like learning algorithm is proposed for the problem. Various extensions of the problem, as well as the corresponding modifications in the proposed algorithm, are discussed. Simulation results of the proposed algorithm for DGVQ and its extensions, are given. 1 Introduction In classical Vector Quantization (VQ), a given stream of data vectors is statistically encoded into a digital sequence suitable for communication over or storage in a digital channel. The goal is to reduce the bit rate so as to minimize communication channel capacity or digital s... | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||