Rolland, Paul Thierry Yves
Kavis, Ali
Immer, Alex
Singla, Adish
Cevher, Volkan
Efficient learning of smooth probability functions from Bernoulli tests with guarantees.
Proceedings of the International Conference on Machine Learning - ICML 2019
Proceedings of the International Conference on Machine Learning - ICML 2019
Proceedings of the International Conference on Machine Learning - ICML 2019
Proceedings of the International Conference on Machine Learning - ICML 2019
20
ml-ai
2019
2019
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.
Proceedings of the International Conference on Machine Learning - ICML 2019
Scheduled publication of Proceedings: Volume 97 is assigned to ICML 2019 (ISSN: 2640-3498)
Conference Papers