Optimizers for 'torch' deep learning library. These
functions include recent results published in the literature and are
not part of the optimizers offered in 'torch'. Prospective users
should test these optimizers with their data, since performance
depends on the specific problem being solved. The packages includes
the following optimizers: (a) 'adabelief' by Zhuang et al (2020),
; (b) 'adabound' by Luo et al.(2019),
; (c) 'adahessian' by Yao et al.(2021)
; (d) 'adamw' by Loshchilov & Hutter (2019),
; (e) 'madgrad' by Defazio and Jelassi (2021),
; (f) 'nadam' by Dozat (2019),
; (g) 'qhadam' by
Ma and Yarats(2019), ; (h) 'radam' by Liu et al.
(2019), ; (i) 'swats' by Shekar and Sochee (2018),
; (j) 'yogi' by Zaheer et al.(2019),
.