Ancestors

Written by Sophie Huiberts on 2024-11-09 at 21:30

remember alphachip, a 2021 google paper that claimed that their RL-based methods outperformed the state-of-the-art methods for chip macro placement?

according to this new meta-analysis, their results dont replicate and are full of errors. there's also been allegations of fraud 👀

https://cacm.acm.org/research/reevaluating-googles-reinforcement-learning-for-ic-macro-placement

=> More informations about this toot | More toots from sophiehuiberts@mathstodon.xyz

Written by Sophie Huiberts on 2024-11-09 at 21:34

people i talked to were already skeptical when it first came out, since shoddy ML-for-optimization papers are published all the time. i am happy that at least for this paper there is robust follow-up on matters of research misconduct

=> More informations about this toot | More toots from sophiehuiberts@mathstodon.xyz

Toot

Written by Sophie Huiberts on 2024-11-09 at 21:34

now we wait for nature to retract the paper

=> More informations about this toot | More toots from sophiehuiberts@mathstodon.xyz

Descendants