Andrew Gordon Wilson
andrewgwils
There is a lot of often overlooked evidence that standard p(w) = N(0, a*I) priors combined with a NN f(x,w) induce a distribution over functions p(f(x)) with useful properties!... 1/15
Read more
In practice, standard "deep ensembles" of independently trained models provides a relatively compelling Bayesian model average. This point is often overlooked because we are used to viewing Bayesian methods as
Read more
I will be taking PhD students in Fall 2021, at NYU Courant Computer Science (Dec 12), Data Science (Dec 12) and Math (Dec 18)! Some details: https://cims.nyu.edu/~andrewgw/group/I am often asked
Read more
By continuing to use the site, you are consenting to the use of cookies as explained in our Cookie Policy to improve your experience.