ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let σ\sigma be an activation function satisfying the mild assumptions in the claim, let Θ\Theta be the parameter space of an MLP, and let f(∙;θ)f(\bullet;\theta) denote the function represented by a parameter θ∈Θ\theta \in \Theta. A parameter θ′∈Θ\theta' \in \Theta is weakly identifiable when it has the weak identifiability property for the MLP parameterization.

Weak identifiability conjecture. With mild assumptions on the activation function σ\sigma, for every parameter θ∈Θ\theta \in \Theta of an MLP, there exists a parameter θ′∈Θ\theta' \in \Theta such that f(∙;θ)=f(∙;θ′)f(\bullet;\theta)=f(\bullet;\theta'), and θ′\theta' is weakly identifiable.

For arbitrary activation functions, this is described as a major open problem in the theory of deep learning; the precise mild assumptions and the weak identifiability property are defined elsewhere in the paper.

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 in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.