We give a bound on the expected reconstruction error for a general coding method where data in a Hilbert space are represented by finite dimensional coding vectors. The result can...
We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we ...
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...
Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks,...
Currently, the most effective complete SAT solvers are based on the DPLL algorithm augmented by clause learning. These solvers can handle many real-world problems from application...
Philipp Hertel, Fahiem Bacchus, Toniann Pitassi, A...