Black Swans

TagLast edit: 15 Sep 2020 23:50 UTC by Ruby

A black swan is a high-impact event that is hard to predict (but not necessarily of low probability). Also, an event that is not accounted for in a model, and therefore causes the model to break down when it occurs.

Considering some event a black swan doesn’t give a leave to not assign any probabilities, since making decisions depending on the plausibility of such event is still equivalent to assigning probabilities that make the expected utility calculation give those decisions.

External posts:

See also

How to Un­der­stand and Miti­gate Risk

Matt Goldenberg12 Mar 2019 10:14 UTC
55 points
30 comments16 min readLW link

Knigh­tian un­cer­tainty in a Bayesian framework

So8res24 Jul 2014 14:31 UTC
39 points
2 comments11 min readLW link

Of Lies and Black Swan Blowups

Eliezer Yudkowsky7 Apr 2009 18:26 UTC
25 points
8 comments1 min readLW link

What’s Hard About Long Tails?

johnswentworth23 Apr 2020 16:32 UTC
24 points
18 comments2 min readLW link

Risk-Free Bonds Aren’t

Eliezer Yudkowsky22 Jun 2007 22:30 UTC
21 points
40 comments2 min readLW link
No comments.