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
Soumya D. Mohanty, Professor of Physics at the University of Texas Rio Grande Valley, completed his PhD degree in 1997 at the Inter-University Center for Astronomy and Astrophysics, India. He subsequently held post-doctoral positions at Northwestern University, Penn State, and the Max-Planck Institute for Gravitational Physics. He was also a visiting scholar with the LIGO project at Caltech. Mohanty's research has focused on solving some of the important data analysis challenges faced in Gravitational Wave (GW) astronomy across all observational frequency bands. These include non-parametric regression of very weak signals in noisy data, high-dimensional non-linear parametric regression, time series classification, and analysis of data from large heterogeneous sensor arrays. Mohanty's work has been funded by grants from the Research Corporation, the U.S. National Science Foundation, and NASA.