Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
The majority of theoretical work in machine learning is done under the assumption of exchangeability: essentially, it is assumed that the examples are generated from the same prob...
Vladimir Vovk, Ilia Nouretdinov, Alexander Gammerm...
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
Retrieval techniques based on pure similarity metrics are often suffered from the scales of image features. An alternative approach is to learn a mapping based on queries and rele...