Semi-Supervised Least-Squares Conditional Density Estimation

Conditional density estimation is an useful alternative to regression to learn an input-output relationship under multi-modality, asymmetry, and heteroscedasticity. The supervised learning method called least-squares conditional density estimation (LSCDE) is the state-of-the-art method that directly estimates the conditional density using a linear model. In this paper, we extend the supervised LSCDE method to a semisupervised scenario so that unlabelled data can be utilized, and numerically illustrates its usefulness.