Diversification-Based Learning in Computing and Optimization
This work provides a novel framework for researchers and practitioners in machine learning and optimization, though it appears incremental as it builds on existing metaheuristic principles.
The paper tackles the problem of creating more flexible and comprehensive intensification and diversification strategies in metaheuristic search by introducing the Diversification-Based Learning (DBL) framework, which unifies and extends earlier proposals to go beyond the Opposition-based learning (OBL) framework.
Diversification-Based Learning (DBL) derives from a collection of principles and methods introduced in the field of metaheuristics that have broad applications in computing and optimization. We show that the DBL framework goes significantly beyond that of the more recent Opposition-based learning (OBL) framework introduced in Tizhoosh (2005), which has become the focus of numerous research initiatives in machine learning and metaheuristic optimization. We unify and extend earlier proposals in metaheuristic search (Glover, 1997, Glover and Laguna, 1997) to give a collection of approaches that are more flexible and comprehensive than OBL for creating intensification and diversification strategies in metaheuristic search. We also describe potential applications of DBL to various subfields of machine learning and optimization.