Abstract | ||
---|---|---|
Multi-fold cross-validation is an established practice to estimate the error rate of a learning algorithm. Quantifying the variance reduction gains due to cross-validation has been challenging due to the inherent correlations introduced by the folds. In this work we introduce a new and weak measure of stability called \emphloss stability and relate the cross-validation performance to loss stability; we also establish that this relationship is near-optimal. Our work thus quantitatively improves the current best bounds on cross-validation. |
Year | Venue | Field |
---|---|---|
2013 | ICML | Mathematical optimization,Computer science,Word error rate,Variance reduction,Cross-validation |
DocType | Citations | PageRank |
Conference | 3 | 0.37 |
References | Authors | |
14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ravi Kumar | 1 | 13932 | 1642.48 |
Daniel Lokshtanov | 2 | 1438 | 110.05 |
Sergei Vassilvitskii | 3 | 2750 | 139.31 |
Andrea Vattani | 4 | 171 | 11.45 |