ott.solvers.linear.acceleration.Momentum#

class ott.solvers.linear.acceleration.Momentum(start=0, error_threshold=inf, value=1.0, inner_iterations=1)[source]#

Momentum for Sinkhorn updates, either constant [Thibault et al., 2021] or adaptive [Lehmann et al., 2021].

Methods

lehmann(state)

Momentum formula [Lehmann et al., 2021], eq.

weight(state, iteration)

Compute momentum term if needed, using previously seen errors.

Attributes

error_threshold

inner_iterations

start

value

Parameters
  • start (int) –

  • error_threshold (float) –

  • value (float) –

  • inner_iterations (int) –

Return type

None