no code implementations • 10 Feb 2019 • Peiran Yu, Guoyin Li, Ting Kei Pong
In addition, for nonconvex models, we show that the KL exponent of many difference-of-convex functions can be derived from that of their natural majorant functions, and the KL exponent of the Bregman envelope of a function is the same as that of the function itself.
no code implementations • 22 Oct 2017 • Peiran Yu, Ting Kei Pong
Iteratively reweighted $\ell_1$ algorithm is a popular algorithm for solving a large class of optimization problems whose objective is the sum of a Lipschitz differentiable loss function and a possibly nonconvex sparsity inducing regularizer.