Abstract
In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals. © 2011 Elsevier B.V.
Original language | English |
---|---|
Pages (from-to) | 1868-1873 |
Journal | Neurocomputing |
Volume | 74 |
Issue number | 11 |
DOIs | |
Publication status | Published - May 2011 |
Externally published | Yes |
Funding
This work is supported by City University Strategic Grant (7002441), the Fundamental Research Funds for the Central Universities, SCUT (2009ZM0081), NSFC(10826053, 60825306, U0735004) and GDSF(07118074).
Keywords
- Convergence
- Global optimum
- Population-Based Incremental Learning (PBIL)