A unified CMI generalization bound based on leave-m-out cross-validation that envelopes existing results, bridges MI/CMI gaps, and sharpens under bounded loss with empirical gains.
Understanding generalization via leave-one-out conditional mutual information,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Unified and Sharpened CMI Bounds for Generalization Errors
A unified CMI generalization bound based on leave-m-out cross-validation that envelopes existing results, bridges MI/CMI gaps, and sharpens under bounded loss with empirical gains.