75 citations · 98 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2014★ 75 cited
Near-Optimally Teaching the Crowd to Classify
Adish Singla, Ilija Bogunovic, Gábor Bartók +2
How should we present training examples to learners to teach them classification rules? This is a natural problem when training workers for crowdsourcing labeling tasks, and is als…
cs.LG2012★ 23 cited
An Adaptive Algorithm for Finite Stochastic Partial Monitoring
Gabor Bartok, Navid Zolghadr, Csaba Szepesvari
We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax…