Expected-dimension conjecture for non-increasing-width polynomial neural networks
Statement
Let be a non-increasing sequence of widths with . For each activation degree , let denote the associated neurovariety, and let its expected dimension be the dimension predicted by the parameter count and ambient dimension.
Non-increasing-width expected-dimension conjecture. For every , the neurovariety attains the expected dimension.
This predicts non-defectivity for architectures whose widths never increase toward the output. The source presents it as a conjecture contrasting with the asymptotic large-activation-degree statement; no resolution is supplied in the provided text.
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.