Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

DOI10.1109/TIT.2011.2182033zbMath1365.94131WikidataQ59679445 ScholiaQ59679445MaRDI QIDQ5271985

Sham M. Kakade, Niranjan Srinivas, Matthias W. Seeger, Andreas Krause

Publication date: 12 July 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Nonparametric regression and quantile regression (62G08) Bayesian problems; characterization of Bayes procedures (62C10) Information theory (general) (94A15)

Related Items (79)

Noisy kriging-based optimization methods: a unified implementation within the DiceOptim package ⋮ An active learning approach for improving the performance of equilibrium based chemical simulations ⋮ Warped Gaussian Processes and Derivative-Based Sequential Designs for Functions with Heterogeneous Variations ⋮ Modelling human active search in optimizing black-box functions ⋮ Likelihood-free inference with deep Gaussian processes ⋮ Quantifying uncertainty with ensembles of surrogates for blackbox optimization ⋮ Unnamed Item ⋮ Constrained, Global Optimization of Unknown Functions with Lipschitz Continuous Gradients ⋮ Personalized optimization with user's feedback ⋮ Deterministic error bounds for kernel-based learning techniques under bounded noise ⋮ On the equivalence of probability spaces ⋮ Automated Reinforcement Learning (AutoRL): A Survey and Open Problems ⋮ Bayesian optimization with partially specified queries ⋮ Adaptive-treed bandits ⋮ Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics ⋮ Online learning‐based model predictive control with Gaussian process models and stability guarantees ⋮ Bayesian policy reuse ⋮ Nonlinear learning‐based model predictive control supporting state and input dependent model uncertainty estimates ⋮ Efficient hybrid Bayesian optimization algorithm with adaptive expected improvement acquisition function ⋮ Multi-fidelity Bayesian optimization to solve the inverse Stefan problem ⋮ TREGO: a trust-region framework for efficient global optimization ⋮ \textsc{GoSafeOpt}: scalable safe exploration for global optimization of dynamical systems ⋮ On the use of Wasserstein distance in the distributional analysis of human decision making under uncertainty ⋮ Inverse Bayesian optimization: learning human acquisition functions in an exploration vs exploitation search task ⋮ Unnamed Item ⋮ Modeling and Active Learning for Experiments with Quantitative-Sequence Factors ⋮ Kernel-based identification with frequency domain side-information ⋮ An asynchronous parallel high-throughput model calibration framework for crystal plasticity finite element constitutive models ⋮ Uncertainty quantification for sparse spectral variational approximations in Gaussian process regression ⋮ Adaptive confidence bound based Bayesian optimization via potentially optimal Lipschitz conditions ⋮ A model‐and data‐driven predictive control approach for tracking of stochastic nonlinear systems using Gaussian processes ⋮ Moderate deviations inequalities for Gaussian process regression ⋮ Strategy synthesis for partially-known switched stochastic systems ⋮ Multi-fidelity cost-aware Bayesian optimization ⋮ Gaussian processes for computer experiments ⋮ Finite-Time Analysis for the Knowledge-Gradient Policy ⋮ Gaussian process bandits with adaptive discretization ⋮ FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks ⋮ Simple Bayesian Algorithms for Best-Arm Identification ⋮ A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions ⋮ Stable Gaussian process based tracking control of Euler-Lagrange systems ⋮ Query efficient posterior estimation in scientific experiments via Bayesian active learning ⋮ Learning Enabled Constrained Black-Box Optimization ⋮ A derivative-free optimization algorithm for the efficient minimization of functions obtained via statistical averaging ⋮ pBO-2GP-3B: a batch parallel known/unknown constrained Bayesian optimization with feasibility classification and its applications in computational fluid dynamics ⋮ Unnamed Item ⋮ On Bayesian index policies for sequential resource allocation ⋮ Residual Gaussian process: a tractable nonparametric Bayesian emulator for multi-fidelity simulations ⋮ MSO: a framework for bound-constrained black-box global optimization algorithms ⋮ An experimental methodology for response surface optimization methods ⋮ Navigating the protein fitness landscape with Gaussian processes ⋮ Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization ⋮ Unnamed Item ⋮ A Bayesian optimization approach to find Nash equilibria ⋮ Truthful Mechanisms with Implicit Payment Computation ⋮ A characterization of amenable groups by Besicovitch pseudodistances ⋮ Simulation optimization: a review of algorithms and applications ⋮ Learning to Optimize via Information-Directed Sampling ⋮ Learning‐based iterative modular adaptive control for nonlinear systems ⋮ Evaluating Gaussian process metamodels and sequential designs for noisy level set estimation ⋮ Deterministic global optimization with Gaussian processes embedded ⋮ Probabilistic Line Searches for Stochastic Optimization ⋮ Analyzing stochastic computer models: a review with opportunities ⋮ Non-parametric probabilistic load flow using Gaussian process learning ⋮ Technical Note—A Note on the Equivalence of Upper Confidence Bounds and Gittins Indices for Patient Agents ⋮ A supermartingale approach to Gaussian process based sequential design of experiments ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Learning to Optimize via Posterior Sampling ⋮ Safe trajectory tracking for underactuated vehicles with partially unknown dynamics ⋮ High-probability stable Gaussian process-supported model predictive control for Lur'e systems ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Learning-based symbolic abstractions for nonlinear control systems ⋮ \texttt{CAMERA}: a method for cost-aware, adaptive, multifidelity, efficient reliability analysis ⋮ A taxonomy of weight learning methods for statistical relational learning ⋮ System design of stochastic models using robustness of temporal properties ⋮ Sequential Design for Ranking Response Surfaces ⋮ Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

This page was built for publication: Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting