Optimal¶ Optimal learning schedule as proposed by Léon Bottou. Parameters¶ loss Type → optim.losses.Loss alpha Default → 0.0001 Methods¶ get Returns the learning rate at a given iteration. Parameters t — 'int' Bottou, L., 2012. Stochastic gradient descent tricks. In Neural networks: Tricks of the trade (pp. 421-436). Springer, Berlin, Heidelberg. ↩