Multi-distribution learning generalizes the classic PAC learning to handle data coming from
multiple distributions. Given a set of $ k $ data distributions and a hypothesis class of VC …

In the framework of online convex optimization, most iterative algorithms require the
computation of projections onto convex sets, which can be computationally expensive. To …

We study the setting of multiclass boosting with a possibly large number of classes. A recent
work by Brukhim, Hazan, Moran, and Schapire, 2021, proved a hardness result for a large …

Boosting is an algorithmic approach which is based on the idea of combining weak and
moderately inaccurate hypotheses to a strong and accurate one. In this work we study …

Let H be a class of boolean functions and consider a composed class H'that is derived from
H using some arbitrary aggregation rule (for example, H'may be the class of all 3-wise …

Reducing reinforcement learning to supervised learning is a well-studied and effective
approach that leverages the benefits of compact function approximation to deal with large …

We study a variant of online optimization in which the learner receives k-rounddelayed
feedback about hitting cost and there is a multi-step nonlinear switching cost, ie, costs …

We consider the problem of online boosting for regression tasks, when only limited
information is available to the learner. This setting is motivated by applications in …

The theory of boosting provides a computational framework for aggregating approximate
weak learning algorithms, which perform marginally better than a random predictor, into an …

Omnipredictors are simple prediction functions that encode loss-minimizing predictions with
respect to a hypothesis class $\H $, simultaneously for every loss function within a class of …