Sequential Bayesian Prediction in the Presence of Changepoints and Faults

By Roman Garnett, Michael A. Osborne, Steven Reece, Alex Rogers, Stephen J. Roberts. 2010

79 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016, background): “There are many other examples of nonstationary covariance functions [3], [22], [54], [70], [118], [121], [126], [132] that have been proposed for GP regression along with closely related output warping techniques [141] that can also model certain kinds of nonstationary processes.”
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010, methodology): “, 2010] and the locations of sensors in a network [Garnett et al., 2010a].”
Automatic Construction and Natural-Language Description of Nonparametric Regression Models (2014, background): “…(squared exponential), a Bayesian variant of multiple kernel learning (MKL) (e.g. Bach, Lanckriet, and Jordan, 2004), change point modeling (e.g. Garnett et al., 2010; Saatc¸i, Turner, and Rasmussen, 2010; Fox and Dunson, 2013), spectral mixture kernels (Wilson and Adams, 2013) (spectral…”
Gaussian processes for time-series modelling (2013, methodology): “[10], a fully Bayesian framework was introduced for performing sequential time-series prediction in the presence of changepoints.”
Gaussian process regression for forecasting battery state of health (2017, background): “GPs have the capability to account for such transitions; specifically, change-point kernels [31,32] could be used to locate change points in an online manner, and hence more accurately model the regimes before and after a transition than would be possible with a single model over the entire domain.”
Active Learning of Model Evidence Using Bayesian Quadrature (2012, methodology): “We model the quasar spectra using a GP; the presence of aDLA is represented as an observation fault with known dynamics [14].”
Identifying Platform Effects in Social Media Data (2016, background): “We note that it may be possible in future work to adapt covariance functions that account for ‘changepoints’ (Garnett et al. 2010) not just to make predictions in the presence of discontinuities, but to do causal inference within the RD framework.”
Automatic model construction with Gaussian processes (2014, background): “, 2004; Gönen and Alpaydın, 2011), changepoint modeling (e.g. Fox and Dunson, 2013; Garnett et al., 2010; Saatçi et al., 2010), spectral mixture kernels (Wilson and Adams, 2013) (spectral kernels), and trend-cyclical-irregular models (e.”
A Gaussian process framework for modelling instrumental systematics: application to transmission spectroscopy (2011, unknown): “A more appropriate choice of covariance kernel is required for such functions (e.g. Garnett et al. 2010).”