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.
Can be 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