Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> You could run a little benchmark and adjust the timing based on that, but there are too many factors.

Or you could train an ML model, like so many academics have been doing: https://arxiv.org/pdf/1211.0906.pdf http://prl.korea.ac.kr/~pronto/home/papers/sas14-leohyi.pdf



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: