Adds a sigma parameter for the momenta target distribution of SGHMC and SGNHT. This is needed to get an equivalence with SGD+momenta when setting temperature=0 as SGD+momenta has three tuning parameters (lr, momentum, dampening) assuming no weight decay.
Adds a sigma parameter for the momenta target distribution of SGHMC and SGNHT. This is needed to get an equivalence with SGD+momenta when setting
temperature=0as SGD+momenta has three tuning parameters (lr, momentum, dampening) assuming no weight decay.