We study the branching program complexity of the tree evaluation problem, introduced in [BCM+09a] as a candidate for separating NL from LogCFL. The input to the problem is a roote...
Mark Braverman, Stephen A. Cook, Pierre McKenzie, ...
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
Selecting the optimal kernel is an important and difficult challenge in applying kernel methods to pattern recognition. To address this challenge, multiple kernel learning (MKL) ...
A fully automatic, compiler-driven approach to parallelisation can result in unpredictable time and space costs for compiled code. On the other hand, a fully manual approach to pa...