Using a Gaussian Hermite basis under a non-Gaussian input produces an exactly quantifiable mismatch penalty, computable in O(s^3) from moments through order 2s.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Exact Computation of Non-Gaussian Mismatch Penalties in Wiener-Hermite Cross-Correlation Identification
Using a Gaussian Hermite basis under a non-Gaussian input produces an exactly quantifiable mismatch penalty, computable in O(s^3) from moments through order 2s.