In the Best-k-Arm problem, we are given n stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the k arms with the largest means by taking as fewâ€¦ (More)

We study the combinatorial pure exploration problem Best-Set in a stochastic multiarmed bandit game. In an Best-Set instance, we are given n stochastic arms with unknown reward distributions, as wellâ€¦ (More)

We consider a collaborative PAC learning model, in which k players attempt to learn the same underlying concept. We ask how much more information is required to learn an accurate classifier for allâ€¦ (More)

In the classical best arm identification (Best-1-Arm) problem, we are given n stochastic bandit arms, each associated with a reward distribution with an unknown mean. Upon each play of an arm, we canâ€¦ (More)

In the Best-K identification problem (Best-K-Arm), we are given N stochastic bandit arms with unknown reward distributions. Our goal is to identify the K arms with the largest means with highâ€¦ (More)

We consider the problem of learning a discrete distribution in the presence of an fraction of malicious data sources. Specifically, we consider the setting where there is some underlyingâ€¦ (More)

Work on implicit utilitarian voting advocates the design of voting rules that maximize utilitarian social welfare with respect to latent utility functions, based only on observed rankings of theâ€¦ (More)

In the appendix, we present the missing proofs in this paper. In Appendix A, we first discuss a specific instance mentioned in Section 1, showing that our upper bound strictly improves previousâ€¦ (More)

We consider the problem of learning a binary classifier from $n$ different data sources, among which at most an $\eta$ fraction are adversarial. The overhead is defined as the ratio between theâ€¦ (More)