It's true. Basically every estimation or inference problem can be solved by MCMC... | Hacker News

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

		blt on Sept 9, 2022 \| parent \| context \| favorite \| on: Some things I realized about AI while contemplatin... It's true. Basically every estimation or inference problem can be solved by MCMC. The only reason not to do so is a lack of computational power.

operator-name on Sept 9, 2022 [–]

The majority of estimation problems have either:

- too much uncertainty - extremely relaxed tolerances for acceptable answers

and are performed in people's heads or simple napkin/grade school maths. It's not about computational power, it's about what's right for the job.

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