Unimodality conjecture for minimal filling neural-network architectures
Statement
Fix the depth , the endpoint widths and , and the activation degree . Let be a width vector, and let mean coordinatewise comparison. An architecture is filling when its neurovariety has the full expected ambient dimension; is minimal when no smaller width vector with the same fixed endpoints has this property.
Unimodality conjecture. Every minimal width vector whose architecture is filling is unimodal: there exists such that is weakly increasing and is weakly decreasing.
The conjecture formalizes the architectural heuristic that a network should first expand its feature capacity and then contract it. The supplied text gives motivation but no proof or resolution.
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.