000264903 001__ 264903
000264903 005__ 20190331142700.0
000264903 037__ $$aCONF
000264903 245__ $$aIterative Classroom Teaching
000264903 260__ $$c2019
000264903 269__ $$a2019
000264903 336__ $$aConference Papers
000264903 520__ $$aWe consider the machine teaching problem in a classroom-like setting wherein the teacher has to deliver the same examples to a diverse group of students. Their diversity stems from differences in their initial internal states as well as their learning rates. We prove that a teacher with full knowledge about the learning dynamics of the students can teach a target concept to the entire classroom using O (min{d,N} log 1/eps) examples, where d is the ambient dimension of the problem, N is the number of learners, and eps is the accuracy parameter. We show the robustness of our teaching strategy when the teacher has limited knowledge of the learners' internal dynamics as provided by a noisy oracle. Further, we study the trade-off between the learners' workload and the teacher's cost in teaching the target concept. Our experiments validate our theoretical results and suggest that appropriately partitioning the classroom into homogenous groups provides a balance between these two objectives.
000264903 700__ $$0251172$$aYeo, Shuqing Teresa
000264903 700__ $$0251171$$aParameswaran, Kamalaruban
000264903 700__ $$aSingla, Adish
000264903 700__ $$aArpit, Merchant
000264903 700__ $$0250115$$aAsselborn, Thibault Lucien Christian
000264903 700__ $$0250292$$aFaucon, Louis Pierre
000264903 700__ $$0240137$$aDillenbourg, Pierre
000264903 700__ $$0243957$$aCevher, Volkan
000264903 7112_ $$a33rd AAAI Conference on Artificial Intelligence$$cHonolulu, Hawaii, USA$$dJanuary 27 – February 1, 2019
000264903 773__ $$t33rd AAAI Conference on Artificial Intelligence
000264903 8560_ $$fgosia.baltaian@epfl.ch
000264903 8564_ $$uhttps://infoscience.epfl.ch/record/264903/files/aaai19-class-paper.pdf$$s5033054
000264903 909C0 $$zMarselli, Béatrice$$xU12179$$pLIONS$$mvolkan.cevher@epfl.ch$$0252306
000264903 909CO $$ooai:infoscience.epfl.ch:264903$$pSTI$$pconf
000264903 960__ $$agosia.baltaian@epfl.ch
000264903 961__ $$aalain.borel@epfl.ch
000264903 973__ $$aEPFL$$rREVIEWED
000264903 980__ $$aCONF
000264903 981__ $$aoverwrite