I don't think it's widely appreciated how spectacularly confusing and un-useful this is. /ht @snoble
-
-
-
@avibryant@snoble this is exactly the reason why one uses an expoential decay in a time window -
-
-
@avibryant I wonder if there is an adversarial strategy in the market that looks for an exploits when others bots make this error
End of conversation
New conversation -
-
-
@avibryant robust statistics are highly underappreciated. -
@j_houg@avibryant "robust moving average" has a tonne of hits — which ones should I read? -
.
@noelwelsh@j_houg ways I like to smooth: LOESS, which is a moving regression; EWMA (which can be computed streaming & in parallel) -
.
@noelwelsh@j_houg and L1TF and variants, which efficiently fit a piecewise linear model (see http://avibryant.github.io/l1tf/ for a demo)
End of conversation
New conversation -
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.