In this work, we consider the optimization formulation of personalized federated learning
recently introduced by Hanzely & Richtarik (2020) which was shown to give an alternative …

In this paper, we study the multi-armed bandit problem in the batched setting where the
employed policy must split data into a small number of batches. While the minimax regret for …

We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is,
algorithms that change its exploration policy as infrequently as possible during regret …

We study the complexity of producing $(\delta,\epsilon) $-stationary points of Lipschitz
objectives which are possibly neither smooth nor convex, using only noisy function …

We suggest a general oracle-based framework that captures parallel stochastic optimization
in different parallelization settings described by a dependency graph, and derive generic …

We resolve the min-max complexity of distributed stochastic convex optimization (up to a log
factor) in the intermittent communication setting, where $ M $ machines work in parallel over …

Motivated by practical needs such as large-scale learning, we study the impact of adaptivity
constraints to linear contextual bandits, a central problem in online learning and decision …

Classical approaches to experimental design assume that intervening on one unit does not
affect other units. There are many important settings, however, where this noninterference …

A landmark result of non-smooth convex optimization is that gradient descent is an optimal
algorithm whenever the number of computed gradients is smaller than the dimension $ d …

In some applications of reinforcement learning, a dataset of pre-collected experience is
already availablebut it is also possible to acquire some additional online data to help …