Slow Feature Analysis as Variational Inference Objective
This provides a novel theoretical perspective on SFA for researchers in machine learning, though it is incremental as it builds on prior linear formulations without achieving full non-linear equivalence.
The paper tackles the problem of interpreting Slow Feature Analysis (SFA) probabilistically by framing it as a variational inference objective, relaxing the linearity constraint to allow the slowness objective to act as a regularizer to a reconstruction loss.
This work presents a novel probabilistic interpretation of Slow Feature Analysis (SFA) through the lens of variational inference. Unlike prior formulations that recover linear SFA from Gaussian state-space models with linear emissions, this approach relaxes the key constraint of linearity. While it does not lead to full equivalence to non-linear SFA, it recasts the classical slowness objective in a variational framework. Specifically, it allows the slowness objective to be interpreted as a regularizer to a reconstruction loss. Furthermore, we provide arguments, why -- from the perspective of slowness optimization -- the reconstruction loss takes on the role of the constraints that ensure informativeness in SFA. We conclude with a discussion of potential new research directions.