Gaussian averaging of quantized neural models yields C∞ surrogates with a local dimension-dependent error bound under a bounded oscillation condition, plus a CLT-based Gaussian envelope for binary perceptrons.
Title resolution pending
1 Pith paper cite this work, alongside 68 external citations. Polarity classification is still indexing.
1
Pith paper citing it
68
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Local Stability and Gaussian Smoothing of Quantized Neural Networks
Gaussian averaging of quantized neural models yields C∞ surrogates with a local dimension-dependent error bound under a bounded oscillation condition, plus a CLT-based Gaussian envelope for binary perceptrons.