For value functions with spatially decaying sensitivity, separable sum-of-local-neighborhood approximations achieve dimension-independent error bounds and neural network representations with polynomially many parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Separable Approximations of Optimal Value Functions and Their Representation by Neural Networks
For value functions with spatially decaying sensitivity, separable sum-of-local-neighborhood approximations achieve dimension-independent error bounds and neural network representations with polynomially many parameters.