Figures & data
Table 1 The generalization gap and its estimates (TIC, FV, LFV) with the standard deviations in setting (i) where
for
and 0 otherwise.
Table 2 The generalization gap and its estimates (TIC, FV, LFV) with the standard deviations in setting (ii), where
.
Table 3 The generalization gap and its estimates (TIC, FV, LFV) with the standard deviations in setting (iii), where
.
Table 4 The generalization gap and LFV for the NN model with n = 50 and T = 3000.
Table 5 The generalization gap and LFV for the NN model with n = 500 and T = 3000.
Table 6 The generalization gap and LFV for the NN model with n = 1000 and T = 3000.
Table 7 CV statistic and training loss + LFV over 20 different initializations. n denotes the number of samples, and denotes the number of parameters used in NN.