ott.neural.networks.layers.conjugate.FenchelConjugateLBFGS#
- class ott.neural.networks.layers.conjugate.FenchelConjugateLBFGS(gtol=0.001, max_iter=10, max_linesearch_iter=10, linesearch_type='backtracking', linesearch_init='increase', increase_factor=1.5)[source]#
Solve for the conjugate using
LBFGS
.- Parameters:
gtol (
float
) – gradient tolerancemax_iter (
int
) – maximum number of iterationsmax_linesearch_iter (
int
) – maximum number of line search iterationslinesearch_type (
Literal
['zoom'
,'backtracking'
,'hager-zhang'
]) – type of line searchlinesearch_init (
Literal
['increase'
,'max'
,'current'
]) – strategy for line search initializationincrease_factor (
float
) – factor by which to increase the step size during the line search
Methods
solve
(f, y[, x_init])Solve for the conjugate.
Attributes