Author

Patricia Medina

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Sharp Reconstruction Bounds for Autoencoders Using the Same Forward Map

It is shown that the least uniform reconstruction-derivative error is 1-M(M-m)/2,0,0, with affine maps attaining this sharp bound at every prescribed depth, with affine maps attaining this sharp bound at every prescribed depth.

Patricia Medina, Hy P. G. Lam · 0 citations