Bayesian Gaussian processes for sequential prediction, optimisation and quadrature

By Michael A. Osborne. 2010

147 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

The Variational Gaussian Process (2015, methodology): “For product kernels, we can further exploit Kronecker structure to allow fast m × m matrix inversion in O ( Pm 1+1 /P ) operations and O ( Pm 2 /P ) storage, where P > 1 is the number of kernel products (Osborne, 2010).”
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010, methodology): “Methods of learning these values more efficiently is currently an active subfield of research (e.g. [Osborne, 2010, Brochu et al., 2010a]).”
Portfolio Allocation for Bayesian Optimization (2010, background): “Examples can be found in robot gait design [26], online path planning [28, 29], intelligent user interfaces for animation [6, 4], algorithm configuration [20], efficient MCMC [34], sensor placement [38, 33], and reinforcement learning [5].”
Variational Auto-encoded Deep Gaussian Processes (2015, methodology): “In this section we consider two supervised learning problem instances: regression and Bayesian optimization (BO) (Osborne, 2010; Snoek et al., 2012b).”
Convergence Rates of Efficient Global Optimization Algorithms (2011, methodology): “Expected improvement performs well in experiments (Osborne, 2010, § 9.5), but little is known about its theoretical properties.”
Bayesian optimisation for Intelligent Environmental Monitoring (2012, background): “Roman Marchant and Fabio Ramos are with the School of Information Technologies, University of Sydney, NSW 2006 Australia.”
Adaptive MCMC with Bayesian Optimization (2012, methodology): “However, a good alternative is to use either classical or Bayesian quadrature to integrate out the hyper-parameters (Osborne, 2010).”
Robust Gaussian Process-Based Global Optimization Using a Fully Bayesian Expected Improvement Criterion (2011, methodology): “An alternative approach using Bayesian quadrature rules [29] has been proposed in [17–19].”
Bayesian Optimization for Synthetic Gene Design (2015, background): “The BO framework [14, 3, 10, 6] allows us to explore the gene design space in order to provide rules to build genes with interesting properties, such as genes that are able to produce proteins of interest, or genes able to act on the cell lifespan.”
Gaussian process regression for forecasting battery state of health (2017, methodology): “They showed that GPs could handle the non-linear data manifested by battery degradation but they concluded that although they were capable of characterizing the uncertainty in the predictions, they lacked long-range predictive capability.”
An Entropy Search Portfolio for Bayesian Optimization (2014, background): “Although from a Bayesian perspective it is clear that the optimal acquisition function requires multi-step planning, this is often much too computationally expensive even for short horizons [Osborne, 2010].”
BoTorch: Programmable Bayesian Optimization in PyTorch (2019, background): “• Robust implementations of models and acquisition functions for BO and active learning, including MC acquisition functions with support for parallel optimization, composite objectives, and asynchronous evaluation.”
Batch Bayesian Optimization via Local Penalization (2015, background): “A number of possible acquisition functions are now available, ranging from fast heuristics [Osborne, 2010, Jones et al., 1998] to non-local entropy-based approaches [Hennig and Schuler, 2012, Hern´andez-Lobato et al., 2014].”