definitiona
Privatelearningimpliesquantumstability AnonymousAuthor(s) Affiliation Address email
Bimpliesthat,ifthesamplecomplexity of learning in modelA or the combinatorial parameterA is SA, then the complexity of learning inmodelBorthe combinatorial parameterBisSB = poly(SA).
84fdbc3ac902561c00871c9b0c226756-Supplemental.pdf
Formally, we view an architecture as aparameterizableobject--a mapping from model weights tofunctions--described byalabeleddirected acyclic graph (DAG)G(V,E).