That does not intuitively make sense to me. I’d need to see an example or more fleshed out argument to be convinced.
(Also, it sounds like an argument for model-wise double descent, but not epoch-wise double descent.)
That does not intuitively make sense to me. I’d need to see an example or more fleshed out argument to be convinced.
(Also, it sounds like an argument for model-wise double descent, but not epoch-wise double descent.)