How do people think about uncertainty estimation of predictions/prediction intervals in machine learning, when you don't believe you are actually estimating the parameters of any kind of "true model"?
Replying to @Aaroth
.@anqi_liu33 works on robust methods. She employed it for safe exploration in learning residual dynamics in drone landing. Robust regression accounts for covariate shift and gives uncertainty bounds for safe exploration http://tensorlab.cms.caltech.edu/users/anima/pubs/safe.pdf … @GuanyaShi @yisongyue
5:03 PM - 16 Jun 2020
0 replies
2 retweets
10 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.