EXPLOITING DECENTRALIZED MULTI-AGENT COORDINATION FOR LARGE-SCALE MACHINE LEARNING PROBLEMS

Abstract

Nowadays, the scale of machine learning problems becomes much larger than before. It raises a huge demand in distributed perception and distributed computation. A multi-agent system provides exceptional scalability for problems like active sensing and data fusion. However, many rich characteristics of large-scale machine learning problems have not been addressed yet such as large input domain, nonstationarity, and high dimensionality. This thesis identifes the challenges related to these characteristics from multi-agent perspective. By exploiting the correlation structure of data in large-scale problems, we propose multiagent coordination schemes that can improve the scalability of the machine learning models while preserving the computation accuracy.