A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for its current task. There may, however, be multiple reasonable policies suggested by prior experience, and the agent must choose between them potentially without any a priori knowledge about their applicability to its curr...

Online sequence prediction is the problem of predicting the next element of a sequence given previous elements. This problem has been extensively studied in the context of individual sequence prediction, where no prior assumptions are made on the origin of the sequence. Individual sequence prediction algorithms work quite well for long sequences, where the algorithm has enough time to learn the...

We consider the problem of prediction with expert advice when the losses of the experts have low-dimensional structure: they are restricted to an unknown d-dimensional subspace. We devise algorithms with regret bounds that are independent of the number of experts and depend only on the rank d. For the stochastic model we show a tight bound of Θp ? dT q, and extend it to a setting of an approxim...

Building classification models from clinical data often requires labeling examples by human experts. However, it is difficult to obtain a perfect set of labels everyone agrees on because medical data are typically very complicated and it is quite common that different experts have different opinions on the same patient data. A solution that has been recently explored by the research community i...

In the field of informetrics, agents are often represented by numeric sequences of non necessarily conforming lengths. There are numerous aggregation techniques of such sequences, e.g., the g-index, the h-index, that may be used to compare the output of pairs of agents. In this paper we address a question whether such impact indices may be used to model experts’ preferences accurately.

Building classification models from clinical data using machine learning methods often relies on labeling of patient examples by human experts. Standard machine learning framework assumes the labels are assigned by a homogeneous process. However, in reality the labels may come from multiple experts and it may be difficult to obtain a set of class labels everybody agrees on; it is not uncommon t...

The standard model for prediction using a pool of experts has an underlying assumption that one of the experts performs well. In this paper, we show that this assumption does not take advantage of situations where both the outcome and the experts' predictions are based on some input which the learner gets to observe too. In particular, we exhibit a situation where each individual expert perform...

The use of domain knowledge in a learner can greatly improve the models it produces. However, high-quality expert knowledge is very difficult to obtain. Traditionally, researchers have assumed that knowledge comes from a single self-consistent source. A little-explored but often more feasible alternative is to use multiple weaker sources. In this paper we take a step in this direction by develo...