Budgeted Prediction with Expert Advice
نویسندگان
چکیده
We consider a budgeted variant of the problem of learning from expert advice with N experts. Each queried expert incurs a cost and there is a given budget B on the total cost of experts that can be queried in any prediction round. We provide an online learning algorithm for this setting with regret after T prediction rounds bounded by
منابع مشابه
Defensive forecasting for optimal prediction with expert advice
The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of “second-guessing” experts, whose advice depends on the learner’s prediction; this paper assumes that the dependence on the learner’s prediction is continuous.
متن کاملBounded-Regret Sequential Learning using Prediction Markets⇤ (Extended Abstract)
We demonstrate a relationship between prediction markets and online learning algorithms by using a prediction market metaphor to develop a new class of algorithms for learning exponential families with expert advice. The specific problem we consider is that of prediction when data is distributed according to a particular member of an exponential family. In such a case, cost function based predi...
متن کاملPrediction with Expert Advice in Games with Unbounded One-Step Gains
The games of prediction with expert advice are considered in this paper. We present some modification of Kalai and Vempala algorithm of following the perturbed leader for the case of unrestrictedly large one-step gains. We show that in general case the cumulative gain of any probabilistic prediction algorithm can be much worse than the gain of some expert of the pool. Nevertheless, we give the ...
متن کاملCollaborative prediction with expert advice
We consider a collaborative variant of prediction with expert advice. In each round, one user wishes to make a prediction, and must choose which expert to follow. The users would like to share their experiences in order to learn faster—ideally they could amortize the same total regret cross the whole community of users. However, some of the users may behave maliciously, distorting their reporte...
متن کاملPrediction with Expert Advice under Discounted Loss
We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted loss.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015