Derives explicit bounds decomposing KL(GP || LNP) into three costs with decay rates O(e^{-c d^{2/d_x}}) for squared-exponential kernels and O(d^{-2ν/d_x}) for Matérn kernels, plus recommendations to predict variance from locations alone and use second-order pooling.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The standard Transformer block arises as a first-order approximation to a polar state estimator on the hypersphere, with a Polar Transformer retaining higher-order terms.
Neural feature maps create expressive kernels that enable fast, scalable, and consistent exact Gaussian process inference for regression and classification.
citing papers explorer
-
Three Costs of Amortizing Gaussian Process Inference with Neural Processes
Derives explicit bounds decomposing KL(GP || LNP) into three costs with decay rates O(e^{-c d^{2/d_x}}) for squared-exponential kernels and O(d^{-2ν/d_x}) for Matérn kernels, plus recommendations to predict variance from locations alone and use second-order pooling.
-
The Transformer as a Polar State Estimator
The standard Transformer block arises as a first-order approximation to a polar state estimator on the hypersphere, with a Polar Transformer retaining higher-order terms.
-
Scalable Gaussian process inference via neural feature maps
Neural feature maps create expressive kernels that enable fast, scalable, and consistent exact Gaussian process inference for regression and classification.