# The variable metric forward-backward splitting algorithm under mild differentiability assumptions

arXiv: https://arxiv.org/abs/1605.00952 · HTML: https://mlsanity.com/paper/1605.00952/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2016.

## Built on by (most cited first, 3 of 3)

- [Adaptive Proximal Gradient Method for Convex Optimization](https://mlsanity.com/paper/2308.02261/) (2023)
- [Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient](https://mlsanity.com/paper/2301.04431/) (2023)
- [On the convergence of adaptive first order methods: proximal gradient and alternating minimization algorithms](https://mlsanity.com/paper/2311.18431/) (2023)

## Abstract (arXiv)

We study the variable metric forward-backward splitting algorithm for convex minimization problems without the standard assumption of the Lipschitz continuity of the gradient. In this setting, we prove that, by requiring only mild assumptions on the smooth part of the objective function and using several types of line search procedures for determining either the gradient descent stepsizes, or the relaxation parameters, one still obtains weak convergence of the iterates and convergence in the objective function values. Moreover, the o(1/k) convergence rate in the function values is obtained if slightly stronger differentiability assumptions are added. We also illustrate several applications including problems that involve Banach spaces and functions of divergence type.