Graph Enhanced High Dimensional Kernel Regression
This work addresses regression problems in high-dimensional spaces for researchers and practitioners, but it appears incremental as it builds on prior generalized linear models with network data.
The paper tackles the problem of improving predictive performance in high-dimensional regression by combining kernel regression with network data, resulting in models that capture nonlinearities and achieve far better predictive performances.
In this paper, the flexibility, versatility and predictive power of kernel regression are combined with now lavishly available network data to create regression models with even greater predictive performances. Building from previous work featuring generalized linear models built in the presence of network cohesion data, we construct a kernelized extension that captures subtler nonlinearities in extremely high dimensional spaces and also produces far better predictive performances. Applications of seamless yet substantial adaptation to simulated and real-life data demonstrate the appeal and strength of our work.