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

Cost is basically time here. "How much compute we can afford" is really "how long we are willing to wait for the result".


Then again, time * size_of_cluster = cost.

If you train on a cluster that costs >$1M/day to operate, the wait time is likely to be a smaller concern than the financial cost, unless you're REALLY in a hurry to beat some competitor.




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

Search: