We consider random logic programs with two-literal rules and study their properties. In particular, we obtain results on the probability that random “sparse” and “dense” pr...
We introduce an alternative to the smoothing technique approach for constrained optimization. As it turns out for any given smoothing function there exists a modification with part...
Both optimization and learning play important roles in a system for intelligent tasks. On one hand, we introduce three types of optimization tasks studied in the machine learning l...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
Testing with random inputs can give surprisingly good results if the distribution of inputs is spread out evenly over the input domain; this is the intuition behind Adaptive Rando...
Ilinca Ciupa, Andreas Leitner, Manuel Oriol, Bertr...