Subgradient methods for sharp weakly convex functions

@inproceedings{Davis2018SubgradientMF,
  title={Subgradient methods for sharp weakly convex functions},
  author={Damek Davis and Dmitriy Drusvyatskiy and Kellie J. MacPhee and Courtney Paquette},
  year={2018}
}
Subgradient methods converge linearly on a convex function that grows sharply away from its solution set. In this work, we show that the same is true for sharp functions that are only weakly convex, provided that the subgradient methods are initialized within a fixed tube around the solution set. A variety of statistical and signal processing tasks come equipped with good initialization, and provably lead to formulations that are both weakly convex and sharp. Therefore, in such settings… CONTINUE READING
1 Citations
42 References
Similar Papers

Citations

Publications citing this paper.

Similar Papers

Loading similar papers…