Takaisin helsinkiin
I am off tomorrow morning to Helsinki for the European Meeting of Statisticians (EMS 2017). Where I will talk on how to handle multiple estimators in Monte Carlo settings (although I have not made enough progress in this direction to include anything truly novel in the talk!) Here are the slides:
I look forward this meeting, as I remember quite fondly the previous one I attended in Budapest. Which was of the highest quality in terms of talks and interactions. (I also remember working hard with Randal Douc on a yet-unfinished project!)
Xi'an's Og 
July 23, 2017 at 10:15 pm
I am actually considering probabilistic numerics, mind you, but have not yet reach the harbour, still as sea!
July 23, 2017 at 8:14 pm
I’m surprised you aren’t building a model to combine the estimates (á la Lindley’s stuff combining subjective opinions or, lord forbid, probabilistic numerics). From there, it should be possible to disregard/down-weight high variance estimators. Probably some of the stuff Mike West did on dynamic models of varying quality (and lots of strong shrinkage priors) would be useful.