Abstract— This work considers a combination classificationregression based framework with the proposal of using learned kernels in modified support vector regression to provide...
Gradient Boosted Regression Trees (GBRT) are the current state-of-the-art learning paradigm for machine learned websearch ranking — a domain notorious for very large data sets. ...
Stephen Tyree, Kilian Q. Weinberger, Kunal Agrawal...
Abstract: We investigate the structure of model selection problems via the bias/variance decomposition. In particular, we characterize the essential structure of a model selection ...
Program dynamic optimization, adaptive to runtime behavior changes, has become increasingly important for both performance and energy savings. However, most runtime optimizations o...
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learn...