Swarm Intelligence Methods for Statistical Regression
A core task in statistical analysis, especially in the era of Big Data, is the fitting of flexible, high-dimensional, and non-linear models to noisy data in order to capture meaningful patterns. This can often result in challenging non-linear and non-convex global optimization problems. The large data volume that must be handled in Big Data applications further increases the difficulty of these problems. Swarm Intelligence Methods for Statistical Regression describes methods from the field of computational swarm intelligence (SI), and how they can be used to overcome the optimization bottleneck encountered in statistical analysis.
- Provides a short, self-contained overview of statistical data analysis and key results in stochastic optimization theory
- Focuses on methodology and results rather than formal proofs
- Reviews SI methods with a deeper focus on Particle Swarm Optimization (PSO)
- Uses concrete and realistic data analysis examples to guide the reader
- Includes practical tips and tricks for tuning PSO to extract good performance in real world data analysis challenges
Chapter 2 Stochastic Optimization Theory
Chapter 3 Evolutionary Computation and Swarm Intelligence
Chapter 4 Particle Swarm Optimization
Chapter 5 PSO Applications
Appendix A Probability Theory
Appendix B Splines
Appendix C Analytical minimization
This book provides a very readable introduction to swarm intelligence methods, which are useful for solving optimization problems that arise in many fields of science and engineering. By focusing on one particular method (Particle Swarm Optimization) applied to two specific problems, Mohanty gives readers a solid foundation for further investigation into other swarm intelligence methods. A must read for any researcher who wants to stay abreast of this relatively new and upcoming field of statistical analysis.
-Prof. Joseph D. Romano, Texas Tech University