An Information-Theoretic Framework for Unifying Active Learning Problems

This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant. We first introduce a novel active learning criterion that subsumes an existing LSE algorithm and achieves state-of-theart performance in LSE problems with a continuous input domain. Then, by exploiting the relationship between LSE and BO, we design a competitive information-theoretic acquisition function for BO that has interesting connections to upper confidence bound and max-value entropy search (MES). The latter connection reveals a drawback of MES which has important implications on not only MES but also on other MES-based acquisition functions. Finally, our unifying information-theoretic framework can be applied to solve a generalized problem of LSE and BO involving multiple level sets in a data-efficient manner. We empirically evaluate the performance of our proposed algorithms using synthetic benchmark functions, a real-world dataset, and in hyperparameter tuning of machine learning models.

[1]  Nando de Freitas,et al.  A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning , 2010, ArXiv.

[2]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[3]  Kian Hsiang Low,et al.  Decentralized active robotic exploration and mapping for probabilistic field classification in environmental sensing , 2012, AAMAS.

[4]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[5]  Larry A. Wasserman,et al.  Active Learning For Identifying Function Threshold Boundaries , 2005, NIPS.

[6]  Kian Hsiang Low,et al.  Bayesian Optimization with Binary Auxiliary Information , 2019, UAI.

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

[8]  Matthew W. Hoffman,et al.  Output-Space Predictive Entropy Search for Flexible Global Optimization , 2016 .

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Kian Hsiang Low,et al.  Decentralized High-Dimensional Bayesian Optimization with Factor Graphs , 2017, AAAI.

[11]  Kian Hsiang Low,et al.  Distributed Batch Gaussian Process Optimization , 2017, ICML.

[12]  Frédéric Galland,et al.  Synthetic aperture Radar oil spill segmentation by stochastic complexity minimization , 2004, IEEE Geoscience and Remote Sensing Letters.

[13]  Jan Peters,et al.  An experimental comparison of Bayesian optimization for bipedal locomotion , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Alkis Gotovos,et al.  Active Learning for Level Set Estimation , 2022 .

[15]  Andreas Krause,et al.  Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation , 2016, NIPS.

[16]  Janardhan Rao Doppa,et al.  Max-value Entropy Search for Multi-Objective Bayesian Optimization , 2020, NeurIPS.

[17]  Kian Hsiang Low,et al.  Nonmyopic Gaussian Process Optimization with Macro-Actions , 2020, AISTATS.

[18]  Zi Wang,et al.  Max-value Entropy Search for Efficient Bayesian Optimization , 2017, ICML.

[19]  Shinya Suzuki,et al.  Multi-objective Bayesian Optimization using Pareto-frontier Entropy , 2020, ICML.

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

[21]  Matthew W. Hoffman,et al.  Predictive Entropy Search for Efficient Global Optimization of Black-box Functions , 2014, NIPS.

[22]  Kian Hsiang Low,et al.  Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond , 2015, AAAI.

[23]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[24]  Ichiro Takeuchi,et al.  Multi-fidelity Bayesian Optimization with Max-value Entropy Search , 2019, ICML.

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

[26]  Marko Wagner,et al.  Geostatistics For Environmental Scientists , 2016 .