Proximal gradient method

This article includes a list of general references, but it lacks sufficient corresponding inline citations. Please help to improve this article by introducing more precise citations. (November 2013) (Learn how and when to remove this message)

Proximal gradient methods are a generalized form of projection used to solve non-differentiable convex optimization problems.

Many interesting problems can be formulated as convex optimization problems of the form

${\displaystyle \operatorname {min} \limits _{x\in \mathbb {R} ^{N}}\sum _{i=1}^{n}f_{i}(x)}$

where ${\displaystyle f_{i}:\mathbb {R} ^{N}\rightarrow \mathbb {R} ,\ i=1,\dots ,n}$ are possibly non-differentiable

, but proximal gradient methods can be used instead.

Proximal gradient methods starts by a splitting step, in which the functions ${\displaystyle f_{1},...,f_{n}}$ are used individually so as to yield an easily

proximal

because each non-differentiable function among ${\displaystyle f_{1},...,f_{n}}$ is involved via its

alternating-direction method of multipliers

, alternating split Bregman are special instances of proximal algorithms.^[2]

For the theory of proximal gradient methods from the perspective of and with applications to statistical learning theory, see proximal gradient methods for learning.

Projection onto convex sets (POCS)

One of the widely used convex optimization algorithms is projections onto convex sets (POCS). This algorithm is employed to recover/synthesize a signal satisfying simultaneously several convex constraints. Let ${\displaystyle f_{i}}$ be the indicator function of non-empty closed convex set ${\displaystyle C_{i}}$ modeling a constraint. This reduces to convex feasibility problem, which require us to find a solution such that it lies in the intersection of all convex sets ${\displaystyle C_{i}}$. In POCS method each set ${\displaystyle C_{i}}$ is incorporated by its

${\displaystyle P_{C_{i}}}$. So in each iteration ${\displaystyle x}$ is updated as

${\displaystyle x_{k+1}=P_{C_{1}}P_{C_{2}}\cdots P_{C_{n}}x_{k}}$

However beyond such problems

are not appropriate and more general operators are required to tackle them. Among the various generalizations of the notion of a convex projection operator that exist, proximal operators are best suited for other purposes.

Examples

Special instances of Proximal Gradient Methods are

• Projected Landweber
• Alternating projection
• Alternating-direction method of multipliers

See also

• Proximal operator
• Proximal gradient methods for learning
• Frank–Wolfe algorithm

Notes

References

• Rockafellar, R. T. (1970). Convex analysis. Princeton: Princeton University Press.
• Combettes, Patrick L.; Pesquet, Jean-Christophe (2011). Fixed-Point Algorithms for Inverse Problems in Science and Engineering. Vol. 49. pp. 185–212.

External links

• Stephen Boyd and Lieven Vandenberghe Book, Convex optimization
• EE364a: Convex Optimization I and EE364b: Convex Optimization II, Stanford course homepages
• EE227A: Lieven Vandenberghe Notes Lecture 18
• ProximalOperators.jl: a Julia package implementing proximal operators.
• ProximalAlgorithms.jl: a Julia package implementing algorithms based on the proximal operator, including the proximal gradient method.
• Proximity Operator repository: a collection of proximity operators implemented in
  Matlab and Python
  .