AI RESEARCH
Manifold-Matching Autoencoders
arXiv CS.AI
•
ArXi:2603.16568v1 Announce Type: cross We study a simple unsupervised regularization scheme for autoencoders called Manifold-Matching (MMAE): we align the pairwise distances in the latent space to those of the input data space by minimizing mean squared error. Because alignment occurs on pairwise distances rather than coordinates, it can also be extended to a lower-dimensional representation of the data, adding flexibility to the method.