Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels

By Felipe A. Tobar, Thang D. Bui, Richard E. Turner. 2015

77 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

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

1. Richard E. Turner
2. Thang D. Bui
3. Yingzhen Li
4. José Miguel Hernández-Lobato
5. Yarin Gal
6. Chao Ma
7. Jianfei Cai
8. Yew-Soon Ong

In Statistical and Nonlinear Physics

1. Yingzhen Li
2. José Miguel Hernández-Lobato
3. Chao Ma
4. Richard E. Turner
5. Yew-Soon Ong
6. Jianfei Cai
7. Haitao Liu
8. Thang D. Bui

Citations in the corpus

• Autoregressive Convolutional Neural Networks for Asynchronous Time Series (2017, background): “ICML, NIPS, AISTATS, UAI), one can notice that time series are often forecast using Gaussian processes (Petelin et al., 2011; Tobar et al., 2015; Hwang et al., 2016), especially when time series are irregularly sampled (Cunningham et al.”
• Variational Implicit Processes (2018, methodology): “, 2016a), where compositions of GP priors are proposed to represent prior over compositional functions; (2) the search and design of kernels for accurate and efficient learning (van der Wilk et al., 2017; Duvenaud et al., 2013; Tobar et al., 2015; Beck & Cohn, 2017; Samo & Roberts, 2015), and (3) de”
• A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation (2016, background): “The VFE approach can also be extended to employ inter-domain variables (Álvarez et al., 2010; Tobar et al., 2015; Matthews et al., 2016).”
• A Unifying Framework for Sparse Gaussian Process Approximation using Power Expectation Propagation (2016, background): “The VFE approach can also be extended to employ inter-domain variables [16,22].”
• When Gaussian Process Meets Big Data: A Review of Scalable GPs (2018, methodology): “The interdomain idea has also been applied to the posterior approximations [71], [76], [172].”
• Differentiable Compositional Kernel Learning for Gaussian Processes (2018, unknown): “Instead of represeting kernel parametrically, Oliva et al. (2016) modeled random feature dimension with stick breaking prior and Tobar et al. (2015) generated functions as the convolution between a white noise process and a linear filter drawn from GP.”