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

DOI10.1109/TIT.2011.2182033zbMATH Open1365.94131WikidataQ59679445 ScholiaQ59679445MaRDI QIDQ5271985FDOQ5271985

Authors: N. Srinivas, Andreas Krause, Sham M. Kakade, Matthias W. Seeger

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)

Cited In (86)

pBO-2GP-3B: a batch parallel known/unknown constrained Bayesian optimization with feasibility classification and its applications in computational fluid dynamics
Learning-based symbolic abstractions for nonlinear control systems
\texttt{CAMERA}: a method for cost-aware, adaptive, multifidelity, efficient reliability analysis
Hyperband: a novel bandit-based approach to hyperparameter optimization
A taxonomy of weight learning methods for statistical relational learning
On the equivalence of probability spaces
Safe trajectory tracking for underactuated vehicles with partially unknown dynamics
An asynchronous parallel high-throughput model calibration framework for crystal plasticity finite element constitutive models
Deterministic error bounds for kernel-based learning techniques under bounded noise
An experimental methodology for response surface optimization methods
Analyzing stochastic computer models: a review with opportunities
A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions
Stable Gaussian process based tracking control of Euler-Lagrange systems
Learning to optimize via information-directed sampling
Sequential design for ranking response surfaces
Learning-based iterative modular adaptive control for nonlinear systems
Streaming kernel regression with provably adaptive mean, variance, and regularization
Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
Residual Gaussian process: a tractable nonparametric Bayesian emulator for multi-fidelity simulations
Navigating the protein fitness landscape with Gaussian processes
Title not available (Why is that?)
An active learning approach for improving the performance of equilibrium based chemical simulations
A supermartingale approach to Gaussian process based sequential design of experiments
On Bayesian index policies for sequential resource allocation
Warped Gaussian processes and derivative-based sequential designs for functions with heterogeneous variations
Probabilistic line searches for stochastic optimization
Deterministic global optimization with Gaussian processes embedded
Online learning‐based model predictive control with Gaussian process models and stability guarantees
Uncertainty quantification for sparse spectral variational approximations in Gaussian process regression
No-regret Bayesian optimization with unknown hyperparameters
A characterization of amenable groups by Besicovitch pseudodistances
Adaptive-treed bandits
Learning Enabled Constrained Black-Box Optimization
Modelling human active search in optimizing black-box functions
Bayesian optimization with partially specified queries
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
System design of stochastic models using robustness of temporal properties
Finite-time analysis for the knowledge-gradient policy
Quantifying uncertainty with ensembles of surrogates for blackbox optimization
Personalized optimization with user's feedback
Efficient hybrid Bayesian optimization algorithm with adaptive expected improvement acquisition function
Title not available (Why is that?)
A Bayesian optimization approach to find Nash equilibria
Title not available (Why is that?)
Simple Bayesian algorithms for best-arm identification
A derivative-free optimization algorithm for the efficient minimization of functions obtained via statistical averaging
MSO: a framework for bound-constrained black-box global optimization algorithms
Evaluating Gaussian process metamodels and sequential designs for noisy level set estimation
Learning to optimize via posterior sampling
Bayesian policy reuse
Constrained, global optimization of unknown functions with Lipschitz continuous gradients
Query efficient posterior estimation in scientific experiments via Bayesian active learning
Non-parametric probabilistic load flow using Gaussian process learning
Noisy kriging-based optimization methods: a unified implementation within the DiceOptim package
Gaussian processes for computer experiments
Truthful mechanisms with implicit payment computation
Gaussian process bandits with adaptive discretization
Multi-fidelity cost-aware Bayesian optimization
High-probability stable Gaussian process-supported model predictive control for Lur'e systems
Likelihood-free inference with deep Gaussian processes
Efficient constitutive parameter identification through optimisation-based techniques: a comparative analysis and novel composite Bayesian optimisation strategy
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks
Modeling and Active Learning for Experiments with Quantitative-Sequence Factors
Knowledge-based modeling of simulation behavior for Bayesian optimization
Kernel-based identification with frequency domain side-information
Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics
Contextual bandits with continuous actions: smoothing, zooming, and adapting
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
Nonlinear learning‐based model predictive control supporting state and input dependent model uncertainty estimates
Strategy synthesis for partially-known switched stochastic systems
Constrained Bayesian Optimization with Lower Confidence Bound
Multi-fidelity Bayesian optimization to solve the inverse Stefan problem
TREGO: a trust-region framework for efficient global optimization
Technical note -- A note on the equivalence of upper confidence bounds and Gittins indices for patient agents
Using simulation to improve sample-efficiency of Bayesian optimization for bipedal robots
Title not available (Why is that?)
Using the knowledge gradient acquisition function in Bayesian optimization when searching for robust solutions
\textsc{GoSafeOpt}: scalable safe exploration for global optimization of dynamical systems
Regularized identification with internal positivity side-information
Tracking control of uncertain nonlinear systems via adaptive Gaussian process prediction and real-time optimisation
A composite Bayesian optimisation framework for material and structural design
On the use of Wasserstein distance in the distributional analysis of human decision making under uncertainty
Lower bounds on the noiseless worst-case complexity of efficient global optimization
Inverse Bayesian optimization: learning human acquisition functions in an exploration vs exploitation search task

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5271985)