For Markov chains Y to X to Z, the excess minimum risk is bounded by generalized divergence measures with target-dependent sub-Gaussian parameters.
Information-theoretic analysis of generalization capability of learning algorithms,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
For Markov chains Y to X to Z, the excess minimum risk is bounded by generalized divergence measures with target-dependent sub-Gaussian parameters.