Quoc Tran-Dinh, UNC-Chapel Hill Dept. of Statistics and Operations Research, Smooth Structures in Convex Functions and Applications to Proximal-Based Methods
In this talk, we demonstrate one way of exploiting smooth structures hidden in convex functions to develop optimization algorithms. Our key idea is to generalize a powerful concept so-called "self-concordance" introduced by Y. Nesterov and A. Nemirovskii to a broader class of convex functions. We show that this structure covers many applications in statistics and machine learning. Then, we develop a…