Online Learning with Costly Features and Labels

  title={Online Learning with Costly Features and Labels},
  author={Navid Zolghadr and G{\'a}bor Bart{\'o}k and Russell Greiner and Andr{\'a}s Gy{\"o}rgy and Csaba Szepesv{\'a}ri},
This paper introduces the online probing problem: In each round, the learner is able to purchase the values of a subset of feature values. After the learner uses this information to come up with a prediction for the given round, he then has the option of paying to see the loss function that he is evaluated against. Either way, the learner pays for both the errors of his predictions and also whatever he chooses to observe, including the cost of observing the loss function for the given round and… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 19 extracted citations