Efficient learning of smooth probability functions from Bernoulli tests with guarantees

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.

[1]  N. L. Johnson,et al.  Multivariate Analysis , 1958, Nature.

[2]  Sandeep Pandey,et al.  Handling Advertisements of Unknown Quality in Search Advertising , 2006, NIPS.

[3]  John Langford,et al.  A Reductions Approach to Fair Classification , 2018, ICML.

[4]  Raphail E. Krichevsky,et al.  The performance of universal encoding , 1981, IEEE Trans. Inf. Theory.

[5]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[6]  Sean M. McNee,et al.  Interfaces for Eliciting New User Preferences in Recommender Systems , 2003, User Modeling.

[7]  Andreas Krause,et al.  Contextual Gaussian Process Bandit Optimization , 2011, NIPS.

[8]  J. Ghosh,et al.  Posterior consistency of logistic Gaussian process priors in density estimation , 2007 .

[9]  A. V. D. Vaart,et al.  BAYESIAN INVERSE PROBLEMS WITH GAUSSIAN PRIORS , 2011, 1103.2692.

[10]  N. Hjort Nonparametric Bayes Estimators Based on Beta Processes in Models for Life History Data , 1990 .

[11]  Zachariah Gompert,et al.  A Continuous Correlated Beta Process Model for Genetic Ancestry in Admixed Populations , 2016, PloS one.

[12]  Andrew Gordon Wilson,et al.  Copula Processes , 2010, NIPS.

[13]  Won Hyuk Chang,et al.  Robot-assisted Therapy in Stroke Rehabilitation , 2013, Journal of stroke.

[14]  Devavrat Shah,et al.  Explaining the Success of Nearest Neighbor Methods in Prediction , 2018, Found. Trends Mach. Learn..

[15]  M. Grzes,et al.  Modeling and Learning for LaCasa , the Location And Context-Aware Safety Assistant , 2012 .

[16]  Arjun K. Gupta,et al.  On three and five parameter bivariate beta distributions , 1985 .

[17]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[18]  David Blei,et al.  Correlated Random Measures , 2015 .

[19]  N. Laird,et al.  Meta-analysis in clinical trials. , 1986, Controlled clinical trials.

[20]  Alan Sunderland,et al.  Effects of Conventional Physical Therapy and Functional Strength Training on Upper Limb Motor Recovery After Stroke: A Randomized Phase II Study , 2009, Neurorehabilitation and neural repair.

[21]  Subhashis Ghosal,et al.  A Review of Consistency and Convergence of Posterior Distribution , 2022 .

[22]  Ingram Olkin,et al.  A bivariate beta distribution , 2003 .

[23]  Jesse Hoey,et al.  Continuous Correlated Beta Processes , 2011, IJCAI.

[24]  Van Der Vaart,et al.  Rates of contraction of posterior distributions based on Gaussian process priors , 2008 .

[25]  A. Tsybakov,et al.  Fast learning rates for plug-in classifiers , 2007, 0708.2321.

[26]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .