Bert Zwart
@bertzwart1
prof @ CWI & TU/e
stochastic OR - probability - rare events - energy systems
father - husband - has-been draughtsplayer - wannabe runner - girevik
ID: 1229829551364149248
http://adamwierman.com/book 18-02-2020 18:06:40
9,9K Tweet
1,1K Followers
267 Following
One teaser Umut U. Simsekli gave, see also the Neurips talk of Adam Wierman in link below, is the following: suppose A,B are normally distributed and you want to maximize E[Ax^2+Bx] with stochastic gradient descent, unit batch size 1/4