Prod is a seminal algorithm in full-information online learning, which has been conjectured to be fundamentally sub-optimal for multi-armed bandits.

In this work we study the problem of actively learning binary classifiers from a given concept class, i.e., learning by utilizing unlabeled data and submitting targeted queries about their labels to a domain expert. We evaluate the quality of our solutions by considering the learning curves they induce, i.e., the rate of

However, privacy is not a free lunch and usually comes at a cost.

We consider the problem of multiclass transductive online learning when the number of labels can be unbounded.

We are interested in a framework of online learning with kernels for low-dimensional, but large-scale and potentially adversarial datasets.

Local differential privacy is a strong notion of privacy in which the provider of the data guarantees privacy by perturbing the data with random noise. In the standard application of local differential privacy the distribution of the noise is constant and known by the learner.

Neural Information Processing Systems http://nips.cc/

Implicit feedback, such as user clicks, although abundant in online information service systems, does not provide substantial evidence on users' evaluation of system's

We introduce the community exploration problem that has many real-world applications such as online advertising.

We also generalize the standard max-divergence to obtain a broader class called Tsallis max-divergences .