quantax.optimizer.sgd_solver

quantax.optimizer.sgd_solver() → Callable[[...], Array]

The plain stochastic gradient descent solver, returning \(x = A^† b / N_s\) without any preconditioning. Used in a QNGD optimizer, it recovers ordinary SGD on the energy instead of the natural gradient.

Returns:

A solver function with two arguments A and b and one output x.