We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its B...
We consider the task of learning to accurately follow a trajectory in a vehicle such as a car or helicopter. A number of dynamic programming algorithms such as Differential Dynami...
J. Zico Kolter, Adam Coates, Andrew Y. Ng, Yi Gu, ...
Exponential models of distributions are widely used in machine learning for classification and modelling. It is well known that they can be interpreted as maximum entropy models u...
The ability to find tables and extract information from them is a necessary component of many information retrieval tasks. Documents often contain tables in order to communicate d...
Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictiona...
Louise Benoit, Julien Mairal, Francis Bach, Jean P...