Randomized (Block) Coordinate Descent Method is an optimization algorithm popularized by Nesterov (2010) and Richtárik and Takáč (2011).
The first analysis of this method, when applied to the problem of minimizing a smooth convex function, was performed by Nesterov (2010).
[1] In Nesterov's analysis the method needs to be applied to a quadratic perturbation of the original function with an unknown scaling factor.
Richtárik and Takáč (2011) give iteration complexity bounds which do not require this, i.e., the method is applied to the objective function directly.
Furthermore, they generalize the setting to the problem of minimizing a composite function, i.e., sum of a smooth convex and a (possibly nonsmooth) convex block-separable function:
are (simple) convex functions.
Example (block decomposition): If
, one may choose
Example (block-separable regularizers): Consider the optimization problem where
is a convex and smooth function.
Smoothness: By smoothness we mean the following: we assume the gradient of
is coordinate-wise Lipschitz continuous with constants
denotes the partial derivative with respect to variable
Nesterov, and Richtarik and Takac showed that the following algorithm converges to the optimal point: Since the iterates of this algorithm are random vectors, a complexity result would give a bound on the number of iterations needed for the method to output an approximate solution with high probability.
It was shown in [2] that if
ϵ ρ
max
max
is an optimal solution (
ρ ∈ ( 0 , 1 )
is a confidence level and
is target accuracy, then
> ϵ ) ≤ ρ
The following Figure shows how
develops during iterations, in principle.
One can naturally extend this algorithm not only just to coordinates, but to blocks of coordinates.
Assume that we have space
This space has 5 coordinate directions, concretely
in which Random Coordinate Descent Method can move.
However, one can group some coordinate directions into blocks and we can have instead of those 5 coordinate directions 3 block coordinate directions (see image).