Information Geometrically Generalized Covariate Shift Adaptation

Abstract

Many machine learning methods assume that the training and test data follow the same distribution. However, in the real world, this assumption is very often violated. In particular, the phenomenon that the marginal distribution of the data changes is called covariate shift, one of the most important research topics in machine learning. We show that the well-known family of covariate shift adaptation methods is unified in the framework of information geometry. Furthermore, we show that parameter search for geometrically generalized covariate shift adaptation method can be achieved efficiently. Numerical experiments show that our generalization can achieve better performance than the existing methods it encompasses.

References in corpus (6)

• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Practical Bayesian Optimization of Machine Learning Algorithms
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
• $\alpha$-Geodesical Skew Divergence