Classifiers that refrain from classification in certain cases can significantly reduce the misclassification cost. However, the parameters for such abstaining classifiers are ofte...
We consider the problem of optimality, in a minimax sense, and adaptivity to the margin and to regularity in binary classification. We prove an oracle inequality, under the margin ...
We present a modification of the algorithm of Dani et al. [8] for the online linear optimization problem in the bandit setting, which with high probability has regret at most O ( ...
Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, S...
In recent years, a fundamental problem structure has emerged as very useful in a variety of machine learning applications: Submodularity is an intuitive diminishing returns proper...
Choosing a suitable feature representation for structured data is a non-trivial task due to the vast number of potential candidates. Ideally, one would like to pick a small, but in...