ISBA 2012 [#2]

As I slept more than three hours last night, I managed to stay concentrated for a larger portion of the talks today, if missing my morning run! Sam Clifford already discussed some of the sessions I attended, with the same impression about Tamara Broderick’s talk: this was an exceptional and brilliant talk, where the focus was absolutely right and avoided technicalities while conveying the ideas (my candidate for the Lindley prize for sure!). I also like Niels Hjort’s survey and reminiscence, delivered in his unique style! The second session about big data was also quite interesting as it addressed a true problem I feel concerned about if unable to provide useful advances… Michael Jordan’s idea of bags of little bootstraps was neat and concretised the vague notions I had of splitting the data into little datasets. It also opened new directions for thinking, quite appropriately since Michael will spend next year in Paris!

Wanting very much to see the Fushimi Inari-Taisha shrine and its red pilars, I shamefully skipped Chris Holmes’ plenary lecture (and hope Chris will pardon me, one day..!). The shrine was actually quite spectacular while a walking distance from the conference (due East, about 20mn). I even managed to take “empty” pictures despite the crowd. The two afternoon sessions on random probabilities and “honest” MCMC were also quite to my taste, again opening news vistas and raising questions. I also managed to take a peek at most posters, even though another hour would have been welcomed, and got several great exchanges along the way.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.