Preetum Nakkiran
where else to find them
bluesky:preetumnakkiran.bsky.social
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Neil Mallinaronce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting | Deep Learning Theory Workshop and Summer School 2022 | 2022-08-01 |
Defines a three-way taxonomy — benign overfitting, tempered overfitting, catastrophic — and claims many interpolating deep nets sit in the middle: nonzero but… | ||
| Is Overfitting Actually Benign? On the Consistency of Interpolating Methods | Deep Learning Theory Symposium 2021 | 2021-12-03 |
Claims that modern overparameterized interpolating methods fail consistency: training MLPs to interpolation on CIFAR with controlled label corruption and on… | ||
| nothing matches | ||