High-Dimensional Gaussian Process Bandits

By Josip Djolonga, Andreas Krause, Volkan Cevher. 2013

189 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): “Recent work has sought to improve the performance of the GP approach through accommodating higher dimensional problems (Wang et al., 2013; Djolonga et al., 2013), input non-stationarities (Snoek et al., 2014) and initialization through meta-learning (Feurer et al., 2015).”
Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016, background): “bandits [89]; Bayes regret bounds for TS [85], [127]; bounds for high-dimensional problems with an underlying low-rank structure [46]; bounds for parallel Bayesian optimization [45]; and improved regret bounds using mutual information [41].”
Multi-fidelity Bayesian Optimisation with Continuous Approximations (2017, background): “This could be addressed by assuming additional structure on f, g (Djolonga et al., 2013; Kandasamy et al., 2015).”
Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics (2016, unknown): “However, this can be scaled up by discovering a low-dimensional subspace of A for Bayesian optimization (Djolonga et al. 2013; Wang et al. 2013) or encoding additional structure in the kernel (Duvenaud et al.”
Online Clustering of Bandits (2014, background): “Within the above scenarios, the widespread adoption of online social networks, where users are engaged in technology-mediated social interactions (making product endorsement and word-of-mouth advertising a common practice), raises further challenges and opportunities to content recommendation…”
On Kernelized Multi-armed Bandits (2017, unknown): “, 2016) and GP-UCB, including the contextual (Krause & Ong, 2011), high-dimensional (Djolonga et al., 2013; Wang et al., 2013), time-varying (Bogunovic et al.”
Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations (2016, background): “This can be alleviated by assuming additional structure in the problem [8, 15].”
Bayesian Optimization with Unknown Constraints (2014, background): “, 2013) and high dimensional problems (Wang et al., 2013; Djolonga et al., 2013).”
Optimization as Estimation with Gaussian Processes in Bandit Settings (2015, background): “Common assumptions are a low-dimensional or simpler underlying structure of f [7, 34, 15].”
Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models (2015, background): “ly relies on structural assumptions about the objective function. In recent work, it was assumed that the objective varies along a low dimensional subspace only (Chen et al., 2012; Wang et al., 2013; Djolonga et al., 2013), or that it takes the form of an additive model (Kandasamy et al., 2015). Thi”
Max-value Entropy Search for Efficient Bayesian Optimization (2017, background): “In the past, high dimensional BO algorithms were developed under various assumptions such as the existence of a lower dimensional function structure (Djolonga et al., 2013; Wang et al., 2013), or an additive function structure where each component is only active on a lower manifold of the space (Li…”
Multi-fidelity Gaussian Process Bandit Optimisation (2016, background): “By assuming additional structure in the bandit problem (Djolonga et al., 2013; Kandasamy et al., 2015) we may alleviate this problem.”