AccSGD: AccSGD

In sjSDM: Scalable Joint Species Distribution Modeling

AccSGD

Description

accelerated stochastic gradient, see Kidambi et al., 2018 for details

Usage

AccSGD(kappa = 1000, xi = 10, small_const = 0.7, weight_decay = 0)

Arguments

kappa	long step
xi	advantage parameter
small_const	small constant
weight_decay	l2 penalty on weights

Value

Anonymous function that returns optimizer when called.

References

Kidambi, R., Netrapalli, P., Jain, P., & Kakade, S. (2018, February). On the insufficiency of existing momentum schemes for stochastic optimization. In 2018 Information Theory and Applications Workshop (ITA) (pp. 1-9). IEEE.

sjSDM documentation built on Sept. 11, 2024, 7:18 p.m.