Re:Double Descent in Human Learning
by jwilber on Wednesday April 26, 2023 @03:11AM
(#35710423)
There’s definitely more to the picture than that - it’s really about how models in the interpolation region behave (see https://mlu-explain.github.io/double-descent/ or https://mlu-explain.github.io/double-descent2/)
[ Parent
| on HN ]