E-viri
Recenzirano
Odprti dostop
-
Beknazaryan, Aleksandr; Sang, Hailin
Statistics & probability letters, November 2022, 2022-11-00, Letnik: 190Journal Article
We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function α before being multiplied by input vectors. We give an example of continuous, piecewise linear function α for which the empirical risk minimizers over the classes of modified ReLU networks with l1 and squared l2 penalties attain, up to a logarithmic factor, the minimax rate of prediction of unknown β-smooth function.
