Learn More
In the rst part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update rule of(More)
We study the problem of learning to accurately rank a set of objects by combining a given collection of ranking or preference functions. This problem of combining preferences arises in several applications, such as that of combining the results of different search engines, or the " collaborative-filtering " problem of ranking movies for a user based on the(More)
In the multiarmed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing(More)
One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the(More)
In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing(More)
The application of boosting procedures to decision tree algorithms has been shown to produce very accurate classiiers. These classi-ers are in the form of a majority v ote over a n umber of decision trees. Unfortunately, these classiiers are often large, complex and diicult to interpret. This paper describes a new type of classiication rule, the alternating(More)
We analyze the “query by committee” algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease(More)