On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient
Optimization and Control
2018-03-20 v1
Abstract
We provide a simple proof for the Fenchel duality between strong convexity and Lipschitz continuous gradient. To this end, we first establish equivalent conditions of convexity for a general function that may not be differentiable. By utilizing these equivalent conditions, we can directly obtain equivalent conditions for strong convexity and Lipschitz continuous gradient. Based on these results, we can easily prove Fenchel duality. Beside this main result, we also identify several conditions that are implied by strong convexity or Lipschitz continuous gradient, but are not necessarily equivalent to them. This means that these conditions are more general than strong convexity or Lipschitz continuous gradient themselves.
Cite
@article{arxiv.1803.06573,
title = {On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient},
author = {Xingyu Zhou},
journal= {arXiv preprint arXiv:1803.06573},
year = {2018}
}