Efficient learning of smooth probability functions from Bernoulli tests with guarantees
Machine Learning
2019-08-26 v3 Machine Learning
Abstract
We 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.
Cite
@article{arxiv.1812.04428,
title = {Efficient learning of smooth probability functions from Bernoulli tests with guarantees},
author = {Paul Rolland and Ali Kavis and Alex Immer and Adish Singla and Volkan Cevher},
journal= {arXiv preprint arXiv:1812.04428},
year = {2019}
}