000265562 001__ 265562
000265562 005__ 20190828113423.0
000265562 037__ $$aCONF
000265562 245__ $$aEfficient learning of smooth probability functions from Bernoulli tests with guarantees.
000265562 260__ $$c2019
000265562 269__ $$a2019
000265562 300__ $$a20
000265562 336__ $$aConference Papers
000265562 500__ $$aScheduled publication of Proceedings: Volume 97 is assigned to ICML 2019 (ISSN: 2640-3498)
000265562 520__ $$aWe study the fundamental problem of learning an unknown, smooth probability function via pointwise Bernoulli tests. We provide a scalable algorithm for efficiently solving this problem with rigorous guarantees. In particular, we prove the convergence rate of our posterior update rule to the true probability function in L2-norm. Moreover, we allow the Bernoulli tests to depend on contextual features, and provide a modified inference engine with provable guarantees for this novel setting. Numerical results show that the empirical convergence rates match the theory, and illustrate the superiority of our approach in handling contextual features over the state-of-the-art.
000265562 6531_ $$aml-ai
000265562 700__ $$0251266$$aRolland, Paul Thierry Yves$$g223583
000265562 700__ $$0254360$$aKavis, Ali$$g279715
000265562 700__ $$aImmer, Alex
000265562 700__ $$aSingla, Adish
000265562 700__ $$0243957$$aCevher, Volkan$$g199128
000265562 7112_ $$dJune 9-15, 2019$$cLong Beach, USA$$a36th International Conference on Machine Learning (ICML 2019)
000265562 773__ $$tProceedings of the International Conference on Machine Learning - ICML 2019
000265562 8560_ $$fpaul.rolland@epfl.ch
000265562 909C0 $$pLIONS$$mvolkan.cevher@epfl.ch$$0252306$$zMarselli, Béatrice$$xU12179
000265562 909CO $$pconf$$pSTI$$ooai:infoscience.epfl.ch:265562
000265562 960__ $$agosia.baltaian@epfl.ch
000265562 961__ $$aalessandra.bianchi@epfl.ch
000265562 973__ $$aEPFL$$rREVIEWED
000265562 980__ $$aCONF
000265562 981__ $$aoverwrite