no code implementations • 10 Nov 2019 • Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran
We consider the large sum of DC (Difference of Convex) functions minimization problem which appear in several different areas, especially in stochastic optimization and machine learning.
no code implementations • 25 Jun 2018 • Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran
In the first variant, DCA-Like, we introduce a new technique to iteratively modify the decomposition of the objective function.
no code implementations • ICML 2017 • Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran
In this paper, we present a stochastic version of DCA (Difference of Convex functions Algorithm) to solve a class of optimization problems whose objective function is a large sum of non-convex functions and a regularization term.
no code implementations • 1 Jul 2014 • Hoai An Le Thi, Tao Pham Dinh, Hoai Minh Le, Xuan Thanh Vo
Considering a common DC approximation of the zero-norm including all standard sparse inducing penalty functions, we studied the consistency between global minimums (resp.