AdaBound {sjSDM} | R Documentation |
AdaBound
Description
adaptive gradient methods with dynamic bound of learning rate, see Luo et al., 2019 for details
Usage
AdaBound(
betas = c(0.9, 0.999),
final_lr = 0.1,
gamma = 0.001,
eps = 1e-08,
weight_decay = 0,
amsbound = TRUE
)
Arguments
betas |
betas |
final_lr |
eps |
gamma |
small_const |
eps |
eps |
weight_decay |
weight_decay |
amsbound |
amsbound |
Value
Anonymous function that returns optimizer when called.
References
Luo, L., Xiong, Y., Liu, Y., & Sun, X. (2019). Adaptive gradient methods with dynamic bound of learning rate. arXiv preprint arXiv:1902.09843.
[Package sjSDM version 1.0.5 Index]