[tahoe-dev] Bayesian Approach to Black Swans

Josh Wilcox wilcoxjg at gmail.com
Sun Apr 5 21:32:35 UTC 2009


  I don't understand why Black Swans should be impossible to model
effectively.
  I've read neither "Fooled by Randomness" nor "The Black Swan", so maybe I
don't know what a "Black Swan" is, but my naive impression is that they are
rare-but-important-events.
  If this is the case then mightn't we guesstimate their frequency with
some, presumably low, confidence due to their elusive nature, and
incorporate that belief into our model?
--J
P.S.--  I am assuming a Bayesian paradigm.
On Sun, Apr 5, 2009 at 12:00 PM, <tahoe-dev-request at allmydata.org> wrote:

> Send tahoe-dev mailing list submissions to
>        tahoe-dev at allmydata.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>        http://allmydata.org/cgi-bin/mailman/listinfo/tahoe-dev
> or, via email, send a message with subject or body 'help' to
>        tahoe-dev-request at allmydata.org
>
> You can reach the person managing the list at
>        tahoe-dev-owner at allmydata.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of tahoe-dev digest..."
>
>
> Today's Topics:
>
>   1. Re: Josh's would-be GSoC proposal (Shawn Willden)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sat, 4 Apr 2009 18:22:09 -0600
> From: Shawn Willden <shawn-tahoe at willden.org>
> Subject: Re: [tahoe-dev] Josh's would-be GSoC proposal
> To: tahoe-dev at allmydata.org
> Message-ID: <200904041822.09974.shawn-tahoe at willden.org>
> Content-Type: text/plain;  charset="iso-8859-1"
>
> On Friday 03 April 2009 05:25:45 pm zooko wrote:
> > Shawn looked at the "The Black Swan", but I think he decided that he
> > knew where it was going after reading only a part of it.
>
> No, I didn't.  I just commented that in the introduction the author seemed
> to
> miss the forest for the trees.  After reading further, he doesn't, he was
> just oversimplifying for the purposes of introducing the concepts.
>
> It's an interesting book.  The sorts of failures I worked on trying to
> model
> are firmly in "Mediocristan", though.  That doesn't rule out the
> possibility
> of Black Swan failure events, but by definition they're impossible to model
> effectively.  The solution is to model what we can, and to treat the
> results
> as an upper bound on reliability.
>
>        Shawn.
>
>
> ------------------------------
>
> _______________________________________________
> tahoe-dev mailing list
> tahoe-dev at allmydata.org
> http://allmydata.org/cgi-bin/mailman/listinfo/tahoe-dev
>
>
> End of tahoe-dev Digest, Vol 25, Issue 4
> ****************************************
>



-- 
"... it didn't read like someone out to carve a headstone for humanity."
--The Nite Owl
http://allmydata.org

At the edge
Symbols become subtleties
Consensus Conceptions
Where we dance

ZZ --> <esc>:wq

Hacking --> Yacking --> Yakking --> .... --> Yak-Wrangling
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://tahoe-lafs.org/pipermail/tahoe-dev/attachments/20090405/7ca63306/attachment.html>


More information about the tahoe-dev mailing list