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.
Constructive Approximation , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.