Conjecture that interpolation by a two-layer neural network using few parameters automatically forces the represented function to have a large Lipschitz constant, thereby…
Statement
Conjecture that interpolation by a two-layer neural network using few parameters automatically forces the represented function to have a large Lipschitz constant, thereby making overparameterization a law of robustness.
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.