Optimal

Optimal learning schedule as proposed by Léon Bottou.

Parameters

• loss ('optim.losses.Loss')

• alpha – defaults to 0.0001

Methods

get

Returns the learning rate at a given iteration.

Parameters

• t ('int')

References

---

1. Bottou, L., 2012. Stochastic gradient descent tricks. In Neural networks: Tricks of the trade (pp. 421-436). Springer, Berlin, Heidelberg. ↩