braintools.optim.MultiStartResult

braintools.optim.MultiStartResult#

class braintools.optim.MultiStartResult(x, fun, converged, n_iter, best_x, best_fun, best_index, history)[source]#

Variables:

x (PyTree) – Final point of every start; leaves have a leading axis of size S.
fun (jax.Array) – Final loss of every start, shape (S,).
converged (jax.Array) – Boolean (S,): the start met the convergence test (and its loss is finite) before max_iter iterations.
n_iter (jax.Array) – Integer (S,): iterations run by every start.
best_x (PyTree) – The point of the start with the lowest finite loss (no leading axis).
best_fun (jax.Array) – Loss of best_x (a scalar).
best_index (jax.Array) – Index of the best start (an integer scalar).
history (jax.Array) – Loss after every iteration, shape (S, max_iter). Entries after a start stopped repeat its final loss.

Methods

`__init__`()
`count`(value, /)	Return number of occurrences of value.
`index`(value[, start, stop])	Return first index of value.

Attributes