Search Results for author:
Found 6 papers, 3 papers with code
Bayesian inference with finitely wide neural networks
On the basis of multivariate Edgeworth expansion, we propose a non-Gaussian distribution in differential form to model a finite set of outputs from a random neural network, and derive the corresponding marginal and conditional properties.
On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel
With Bochner's theorem, DGP with squared exponential kernel can be viewed as a deep trigonometric network consisting of the random feature layers, sine and cosine activation units, and random weight layers.
Conditional Deep Gaussian Processes: empirical Bayes hyperdata learning
Preliminary extrapolation results demonstrate expressive power from the depth of hierarchy by exploiting the exact covariance and hyperdata learning, in comparison with GP kernel composition, DGP variational inference and deep kernel learning.
Conditional Deep Gaussian Processes: multi-fidelity kernel learning
Recently, [1] pointed out that the hierarchical structure of DGP well suited modeling the multi-fidelity regression, in which one is provided sparse observations with high precision and plenty of low fidelity observations.
Interpretable deep Gaussian processes with moments
We propose interpretable DGP based on approximating DGP as a GP by calculating the exact moments, which additionally identify the heavy-tailed nature of some DGP distributions.
Standing Wave Decomposition Gaussian Process
We propose a Standing Wave Decomposition (SWD) approximation to Gaussian Process regression (GP).
