Stochastic Gradient Langevin Dynamics (SGLD) optimization
Usage
sgld(stepsize = 0.001, temperature = 1)
Arguments
- stepsize
base stepsize
- temperature
non-negative Langevin temperature
Value
a list of control variables for optimization
(used in control_opt function)
Details
SGLD adds Gaussian noise to vanilla SGD updates:
$$x_{t+1} = x_t - \eta_t \nabla U(x_t) + \sqrt{2 T \eta_t}\,\xi_t, \quad \xi_t \sim \mathcal{N}(0, I)$$
where \(T\) is temperature. The implementation applies this
component-wise using the current effective stepsize.
