A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...
Many current state-of-the-art planners rely on forward heuristic search. The success of such search typically depends on heuristic distance-to-the-goal estimates derived from the ...
Spectral clustering is useful for a wide-ranging set of applications in areas such as biological data analysis, image processing and data mining. However, the computational and/or...
Ling Huang, Donghui Yan, Michael I. Jordan, Nina T...
Motivated by applications like elections, web-page ranking, revenue maximization etc., we consider the question of inferring popular rankings using constrained data. More specific...
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...