Deep supervised learners for exponential-family outcomes achieve test-error rates set by the 2β-entropic dimension of the input distribution, improving on Minkowski-dimension-based bounds.
S., Ghosh, J., and Lafferty, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data
Deep supervised learners for exponential-family outcomes achieve test-error rates set by the 2β-entropic dimension of the input distribution, improving on Minkowski-dimension-based bounds.