A non-parametric conditional factor regression model for high-dimensional input and response
This addresses regression challenges in high-dimensional domains, but appears incremental as it builds on linear regression with latent factors.
The paper tackles the problem of regression with high-dimensional input and response by proposing a non-parametric conditional factor regression model, which achieves remarkable prediction performance compared to alternatives.
In this paper, we propose a non-parametric conditional factor regression (NCFR)model for domains with high-dimensional input and response. NCFR enhances linear regression in two ways: a) introducing low-dimensional latent factors leading to dimensionality reduction and b) integrating an Indian Buffet Process as a prior for the latent factors to derive unlimited sparse dimensions. Experimental results comparing NCRF to several alternatives give evidence to remarkable prediction performance.