AndersonAccelerationConfig

class deepinv.optim.AndersonAccelerationConfig(history_size=0.1, beta=0.9, eps=20)

Bases: object

Configuration parameters for Anderson acceleration of a fixed-point algorithm.

Parameters:

• history_size (int) – Number of past iterates used in Anderson acceleration.

• beta (float) – Momentum coefficient in Anderson acceleration.

• eps (float) – Regularization parameter for Anderson acceleration.