Nicholas M. Boffi
@nmboffi.bsky.social
Building generative models for high-dimensional science and engineering.
Assistant prof. @CarnegieMellon & affiliated faculty @mldcmu, previously instructor @NYU_Courant, PhD jointly @Harvard and @MIT
https://nmboffi.github.io
Assistant prof. @CarnegieMellon & affiliated faculty @mldcmu, previously instructor @NYU_Courant, PhD jointly @Harvard and @MIT
https://nmboffi.github.io
isn't the basic idea that you want the bregman divergence to be strongly convex with respect to a norm \Vert\cdot\Vert such that the gradients are bounded in the corresponding dual norm? see below for a slide from my phd thesis -- this is covered in the cited textbook by Nemirovsky and Yudin
January 29, 2025 at 1:14 PM
isn't the basic idea that you want the bregman divergence to be strongly convex with respect to a norm \Vert\cdot\Vert such that the gradients are bounded in the corresponding dual norm? see below for a slide from my phd thesis -- this is covered in the cited textbook by Nemirovsky and Yudin