papers
Publications (2)
stat.ML2020
Cross-validation Confidence Intervals for Test Error
Pierre Bayle, Alexandre Bayle, Lucas Janson +1
This work develops central limit theorems for cross-validation and consistent estimators of its asymptotic variance under weak stability conditions on the learning algorithm. Toget…
stat.ML2026
The Relative Instability of Model Comparison with Cross-validation
Alexandre Bayle, Lucas Janson, Lester Mackey
Cross-validation (CV) is known to provide asymptotically exact tests and confidence intervals for model improvement but only when the model comparison is relatively stable. Surpris…