Reducing variability of crossvalidation for smoothing-parameter choice

48 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation (2010, background): “…selection criterion are likely to be similar to the tried and tested solutions to the problem of over-ﬁtting the training criterion, namely regularisation (Cawley and Talbot, 2007), early stopping (Qi et al., 2004) and model or hyper-parameter averaging (Cawley, 2006; Hall and Robinson, 2009).”