Skip to yearly menu bar Skip to main content


Efficient Second Order Online Learning by Sketching

Haipeng Luo · Alekh Agarwal · Nicolò Cesa-Bianchi · John Langford

Area 5+6+7+8 #17

Keywords: [ Convex Optimization ] [ Online Learning ]


We propose Sketched Online Newton (SON), an online second order learning algorithm that enjoys substantially improved regret guarantees for ill-conditioned data. SON is an enhanced version of the Online Newton Step, which, via sketching techniques enjoys a running time linear in the dimension and sketch size. We further develop sparse forms of the sketching methods (such as Oja's rule), making the computation linear in the sparsity of features. Together, the algorithm eliminates all computational obstacles in previous second order online learning approaches.

Live content is unavailable. Log in and register to view live content