Differentiable Compositional Kernel Learning for Gaussian Processes
By Guodong Zhang, Chaoqi Wang, Wenyuan Zeng, Jiaman Li, Roger Baker Grosse. 2018
77 citations recorded by the source corpus.
The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexible family of kernels represented by a neural network. The NKN architecture is based on the composition rules for kernels, so that each unit of the network corresponds to a valid kernel. It can compactly approximate compositional kernel structures such as those used by the Automatic Statistician (Lloyd et al., 2014), but because the architecture is differentiable, it is end-to-end trainable with gradient-based optimization. We show that the NKN is universal for the class of stationary kernels. Empirically we demonstrate pattern discovery and extrapolation abilities of NKN on several tasks that depend crucially on identifying the underlying structure, including time series and texture extrapolation, as well as Bayesian optimization.
Subfields: Artificial Intelligence, Signal Processing
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
- Yee Whye Teh
- Sergey Levine
- Ruslan Salakhutdinov
- Yoshua Bengio
- Guodong Zhang
- Roger Baker Grosse
- Danilo Jimenez Rezende
- Jiaxin Shi
In Signal Processing
- S. M. Ali Eslami
- Yee Whye Teh
- Danilo Jimenez Rezende
- Roger Baker Grosse
- Jiaxin Shi
- Guodong Zhang
- Fabio Viola
- David M. Blei
Citations in the corpus
- Neural Processes (2018, background): “, 2011) or networks where each unit represents a different kernel (Sun et al., 2018).”
- Functional Variational Bayesian Neural Networks (2019, methodology): “For the prior of the fBNNs, we use a GP with Neural Kernel Network (NKN) kernels as used in [32].”
- Deep convolutional Gaussian processes (2018, background): “Deep Gaussian processes boost performance by modelling networks of GP nodes (Duvenaud et al., 2011; Sun et al., 2018) or by mapping inputs through multiple Gaussian process ’layers’ (Damianou and Lawrence, 2013; Salimbeni and Deisenroth, 2017).”