A neural-network posterior can be written as a log-concave mixture when the parameter count is large, making sampling tractable, with separate risk guarantees of N^{-1/4} and N^{-1/3} for a discrete-prior variant.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rapid Bayesian Computation and Estimation for Neural Networks via Log-Concave Coupling
A neural-network posterior can be written as a log-concave mixture when the parameter count is large, making sampling tractable, with separate risk guarantees of N^{-1/4} and N^{-1/3} for a discrete-prior variant.