A1027
Title: Wrapped Gaussian process functional regression model for batch data on Riemannian manifold
Authors: Jian Qing Shi - Southern Univesity of Science and Technology (China) [presenting]
Abstract: Regression is an essential and fundamental methodology in statistical analysis. Plenty of literature focuses on linear and nonlinear regression in the context of the Euclidean space. However, regression models in non-Euclidean spaces deserve more attention since people observed enormous manifold-valued data. Taking the advantage of massive manifold valued data, this talk will discuss a concurrent functional regression model for batch data on Riemannian manifolds by estimating both mean structure and covariance structure simultaneously. The response variable is considered to follow a wrapped Gaussian process distribution. A nonlinear relationship between manifold valued response variables and multiple Euclidean covariates can be captured by this model in which the covariates could be functional and scalar. The performance of the model has been tested on both simulated data and real data, which endorses it is an effective and efficient tool in conducting functional data regression on Riemannian manifolds.
