Asymptotic expected-dimension conjecture for polynomial neural network neurovarieties
Statement
Let be a fixed vector of widths, with for , and let denote the activation degree. The neurovariety is the image variety associated with this architecture, and its expected dimension is the dimension predicted by the parameter count and ambient dimension.
Asymptotic expected-dimension conjecture. There exists a threshold such that, whenever , the neurovariety attains the expected dimension.
The claim concerns eventual non-defectivity as the activation degree grows. It was previously asserted as a theorem, but the proof contained a mistake; the statement has subsequently been proved in the cited work on activation functions.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.