activity
20062023
most citedEfficient Learning with Partially Observed Attributes

59 citations · 570 across the 34 of their papers we have counts for

collaborators
Showing 2013Show all

7 papers · 1 filter

cs.LG2013★ 31 cited

From Bandits to Experts: A Tale of Domination and Independence

Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile +1

We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir. Our main result is a characterization of regret in the directed observability…

cs.LG2013

A Gang of Bandits

Nicolò Cesa-Bianchi, Claudio Gentile, Giovanni Zappella

Multi-armed bandit problems are receiving a great deal of attention because they adequately formalize the exploration-exploitation trade-offs arising in several industrially releva…

cs.LG2013

See the Tree Through the Lines: The Shazoo Algorithm -- Full Version --

Fabio Vitale, Nicolo Cesa-Bianchi, Claudio Gentile +1

Predicting the nodes of a given graph is a fascinating theoretical problem with applications in several domains. Since graph sparsification via spanning trees retains enough inform…

cs.LG2013★ 1 cited

A Correlation Clustering Approach to Link Classification in Signed Networks -- Full Version --

Nicolo Cesa-Bianchi, Claudio Gentile, Fabio Vitale +1

Motivated by social balance theory, we develop a theory of link classification in signed networks using the correlation clustering index as measure of label regularity. We derive l…

cs.LG2013

A Linear Time Active Learning Algorithm for Link Classification -- Full Version --

Nicolo Cesa-Bianchi, Claudio Gentile, Fabio Vitale +1

We present very efficient active learning algorithms for link classification in signed networks. Our algorithms are motivated by a stochastic model in which edge labels are obtaine…

cs.LG2013★ 50 cited

Online Learning with Switching Costs and Other Adaptive Adversaries

Nicolo Cesa-Bianchi, Ofer Dekel, Ohad Shamir

We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We me…