Contextual Gaussian Process Bandit Optimization

By Andreas Krause, Cheng Soon Ong. 2011

445 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Scalable Bayesian Optimization Using Deep Neural Networks (2015, background): “…including elegant theoretical results (Srinivas et al., 2010; Bull, 2011; de Fre-itas et al., 2012), multitask and transfer optimization (Krause & Ong, 2011; Swersky et al., 2013; Bar-denet et al., 2013) and the application to diverse tasks such as sensor set selection (Garnett et al.,…”
Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016, background): “property within the Bayesian optimization framework [12], [49], [79], [89], [148], [160].”
Input Warping for Bayesian Optimization of Non-Stationary Functions (2014, methodology): “In Krause and Ong [2011], this idea was applied to ﬁnd peptide sequences that bind to molecules for vaccine design, while in Swersky et al. [2013] it was applied to hyperparameter optimization.”
Parallelizing Exploration-Exploitation Tradeoffs with Gaussian Process Bandit Optimization (2012, background): “(2010), as considered for experimental design by Krause and Ong (2011). This database describes the binding affinity of various peptides with a Major Histocompatibility Complex (MHC) Class I molecule, of importance when designing vaccines to exploit peptide binding properties.”
Max-value Entropy Search for Efficient Bayesian Optimization (2017, background): “…optimization of nonconvex, expensive functions in robotics, machine learning, computer vision, and many other areas of science and engineering (Brochu et al., 2009; Calandra et al., 2014; Krause & Ong, 2011; Lizotte et al., 2007; Snoek et al., 2012; Thornton et al., 2013; Wang et al., 2017).”
Neural Contextual Bandits with UCB-based Exploration (2019, methodology): “A third approach uses nonparametric modeling, such as per-ceptrons (Kakade et al., 2008), random forests (F ´ eraud et al., 2016), Gaussian processes and kernels (Kleinberg et al., 2008; Srinivas et al., 2010; Krause & Ong, 2011; Bubeck et al., 2011).”
Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences (2018, methodology): “We use the contextual GP-UCB acquisition function [30]”
Multi-Task Learning for Contextual Bandits (2017, background): “Contextual Gaussian Process UCB (CGP-UCB) builds on GP-UCB and has many elements in common with our framework [10].”
Optimization as Estimation with Gaussian Processes in Bandit Settings (2015, methodology): “Recent successful applications of thisBayesian optimizationframework include the tuning of hyperparameters for complex models and algorithms in machine learning, robotic s, and computer vision [3, 6, 16, 19, 29, 33].”
Introduction to Multi-Armed Bandits (2019, methodology): “The weighted majority algorithm is from Littlestone and Warmuth (1994), and Hedge algorithm is from Littlestone and Warmuth (1994); Freund and Schapire (1997).”
Multi-Task Bayesian Optimization (2013, background): “This approach can be thought of as a special case of contextual Gaussian process bandits [19].”
Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics (2016, unknown): “In normal Bayesian optimization, it was shown by Krause and Ong (2011) that an algorithm that optimizes the GP-UCB criterion in (7) for a ﬁxed context converges to the global optimum after repeatedly seeing the corresponding context.”
Gaussian Process Optimization with Mutual Information (2013, methodology): “One can reduce drastically the computational time by means of Lazy Variance Calculation Desautels et al. [2012], built on the fact that σ2T (x) always decreases for increasing T and for all x ∈ X .”
Automatic Database Management System Tuning Through Large-scale Machine Learning (2017, background): “, making decisions based on existing knowledge) [32, 45].”
ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Language (2019, background): “For example, systems may have complex noise [42, 22], yield multiple types of observations [12], depend on covariates [25], have interrelated subsystems [47], and more.”
Online Clustering of Bandits (2014, methodology): “…(e.g., (Auer, 2002; Langford & Zhang, 2007; Li et al., 2010; Chu et al., 2011; Bogers, 2010; AbbasiYadkori et al., 2011; Crammer & Gentile, 2011; Krause & Ong, 2011), and references therein) have rapidly become a * reference algorithmic technique for implementing adaptive recommender systems.”
Explore-exploit in top-N recommender systems via Gaussian processes (2014, methodology): “Our algorithm extends and generalizes the work of [24, 15, 8].”
Bayesian Optimization with Unknown Constraints (2014, background): “Recent work has extended Bayesian optimization to multiple tasks and objectives (Krause and Ong, 2011; Swersky et al., 2013; Zuluaga et al., 2013) and high dimensional problems (Wang et al., 2013; Djolonga et al., 2013).”
Multiple Adaptive Bayesian Linear Regression for Scalable Bayesian Optimization with Warm Start (2017, methodology): “We perform transfer learning with standard GPs by stacking all observations together and augmenting the input space with the corresponding contextual information [14].”