running some method comparisons, aiming to demonstrate superiority of one parameter set amusingly running into the problem not that the experimental parameters don't improve things, but that the baseline parameterization is implausibly garbage
-
Show this thread
-
curiouser and curiouser outcome for the method is a two stage regression, first stage is used to generate weights for the second stage the first stage runs just fine for the baseline parameterization but the second stage goes absolutely sideways hmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm
1 reply 0 retweets 3 likesShow this thread -
oh good there are tons and tons of negative weights well that explains that fuck fuck fuck
2 replies 0 retweets 2 likesShow this thread -
Replying to @mattguttmanorg
ME TOO I can probably ratfuck around it
1:55 PM - 10 Jul 2018
0 replies
0 retweets
1 like
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.