Side-effects of Learning from Low Dimensional Data Embedded in an Euclidean Space. (arXiv:2203.00614v3 [cs.LG] UPDATED)

The low dimensional manifold hypothesis posits that the data found in many
applications, such as those involving natural images, lie (approximately) on
low dimensional manifolds embedded in a high dimensional Euclidean space. In
this setting, a typical neural network defines a function that takes a finite
number of vectors in the embedding space as input. However, one often needs to
consider evaluating the optimized network at points outside the training
distribution. This paper considers the case in which the training …

arxiv data effects embedded learning lg side-effects space