Definition and Convergence of Iteratively Reweighted Least Squares

I’ve been using iteratively reweighted least squares (IRLS) to minimize functions of the following form,


where N is the number of instances of xiR, mR is the robust estimate that I want, and ρ is a suitable robust penalty function. Let’s say it’s convex (though not necessarily strictly) and differentiable for now. A good example of such a ρ is the Huber loss function.

What I’ve been doing is differentiating J(m) with respect to m (and manipulating) to obtain,


and iteratively solving this by setting it equal to 0 and fixing weights at iteration k to wi(k)=ρ(|xim(k)|)|xim(k)| (note that the perceived singularity at xi=m(k) is really a removable singularity in all ρ‘s I might care about). Then I obtain,


and I solve to obtain, m(k+1)=Ni=1wi(k)xiNi=1wi(k).

I repeat this fixed point algorithm until “convergence”. I will note that if you get to a fixed point, you are optimal, since your derivative is 0 and it’s a convex function.

I have two questions about this procedure:

  1. Is this the standard IRLS algorithm? After reading several papers on the topic (and they were very scattered and vague about what IRLS is) this is the most consistent definition of the algorithm I can find. I can post the papers if people want, but I actually didn’t want to bias anyone here. Of course, you can generalize this basic technique to many other types of problems involving vector xi‘s and arguments other than |xim(k)|, providing the argument is a norm of an affine function of your parameters. Any help or insight would be great on this.
  2. Convergence seems to work in practice, but I have a few concerns about it. I’ve yet to see a proof of it. After some simple Matlab simulations I see that one iteration of this is not a contraction mapping (I generated two random instances of m and computing |m1(k+1)m2(k+1)||m1(k)m2(k)| and saw that this is occasionally greater than 1). Also the mapping defined by several consecutive iterations is not strictly a contraction mapping, but the probability of the Lipschitz constant being above 1 gets very low. So is there a notion of a contraction mapping in probability? What is the machinery I’d use to prove that this converges? Does it even converge?

Any guidance at all is helpful.

Edit: I like the paper on IRLS for sparse recovery/compressive sensing by Daubechies et al. 2008 “Iteratively Re-weighted Least Squares Minimization for Sparse Recovery” on the arXiv. But it seems to focus mostly on weights for nonconvex problems. My case is considerably simpler.


As for your first question, one should define “standard”, or acknowledge that a “canonical model” has been gradually established. As a comment indicated, it appears at least that the way you use IRWLS is rather standard.

As for your second question, “contraction mapping in probability” could be linked (however informally) to convergence of “recursive stochastic algorithms”. From what I read, there is a huge literature on the subject mainly in Engineering. In Economics, we use a tiny bit of it, especially the seminal works of Lennart Ljung -the first paper was Ljung (1977)– which showed that the convergence (or not) of a recursive stochastic algorithm can be determined by the stability (or not) of a related ordinary differential equation.

(what follows has been re-worked after a fruitful discussion with the OP in the comments)


I will use as reference Saber Elaydi “An Introduction to Difference Equations”, 2005, 3d ed.
The analysis is conditional on some given data sample, so the xs are treated as fixed.

The first-order condition for the minimization of the objective function, viewed as a recursive function in m,

has a fixed point (the argmin of the objective function).
By Theorem 1.13 pp 27-28 of Elaydi, if the first derivative with respect to m of the RHS of [1], evaluated at the fixed point m, denote it A(m), is smaller than unity in absolute value, then m is asymptotically stable (AS). More over by Theorem 4.3 p.179 we have that this also implies that the fixed point is uniformly AS (UAS).
“Asymptotically stable” means that for some range of values around the fixed point, a neighborhood (m±γ), not necessarily small in size, the fixed point is attractive , and so if the algorithm gives values in this neighborhood, it will converge. The property being “uniform”, means that the boundary of this neighborhood, and hence its size, is independent of the initial value of the algorithm. The fixed point becomes globally UAS, if γ=.
So in our case, if we prove that


we have proven the UAS property, but without global convergence. Then we can either try to establish that the neighborhood of attraction is in fact the whole extended real numbers, or, that the specific starting value the OP uses as mentioned in the comments (and it is standard in IRLS methodology), i.e. the sample mean of the x's, ˉx, always belongs to the neighborhood of attraction of the fixed point.

We calculate the derivative






we have


Inserting this into [3] we have

\left|\sum_{i=1}^{N}\frac {x_i-m^*}{|x_i-m^*|^2}\cdot \left[w_i(m^*)-\rho''(|x_i-m^*|)\right](x_i-m^*)\right| < \left|\sum_{i=1}^{N} w_i(m^*)\right|

\Rightarrow \left|\sum_{i=1}^{N}w_i(m^*)-\sum_{i=1}^{N}\rho''(|x_i-m^*|)\right| < \left|\sum_{i=1}^{N} w_i(m^*)\right| \qquad [4]

This is the condition that must be satisfied for the fixed point to be UAS. Since in our case the penalty function is convex, the sums involved are positive. So condition [4] is equivalent to

\sum_{i=1}^{N}\rho''(|x_i-m^*|) < 2\sum_{i=1}^{N}w_i(m^*) \qquad [5]

If \rho(|x_i-m|) is Hubert's loss function, then we have a quadratic (q) and a linear (l) branch,

\rho(|x_i-m|)=\cases{ (1/2)|x_i- m|^2 \qquad\;\;\;\; |x_i-m|\leq \delta \\
\delta\big(|x_i-m|-\delta/2\big) \qquad |x_i-m|> \delta}


\rho'(|x_i-m|)=\cases{ |x_i- m| \qquad |x_i-m|\leq \delta \\
\delta \qquad \qquad \;\;\;\; |x_i-m|> \delta}

\rho''(|x_i-m|)=\cases{ 1\qquad |x_i-m|\leq \delta \\
0 \qquad |x_i-m|> \delta}

\cases{ w_{i,q}(m) =1\qquad \qquad \qquad |x_i-m|\leq \delta \\
w_{i,l}(m) =\frac {\delta}{|x_i-m|} <1 \qquad |x_i-m|> \delta}

Since we do not know how many of the |x_i-m^*|'s place us in the quadratic branch and how many in the linear, we decompose condition [5] as (N_q + N_l = N)

\sum_{i=1}^{N_q}\rho_q''+\sum_{i=1}^{N_l}\rho_l'' < 2\left[\sum_{i=1}^{N_q}w_{i,q} +\sum_{i=1}^{N_l}w_{i,l}\right]

\Rightarrow N_q + 0 < 2\left[N_q +\sum_{i=1}^{N_l}w_{i,l}\right] \Rightarrow 0 < N_q+2\sum_{i=1}^{N_l}w_{i,l}

which holds. So for the Huber loss function the fixed point of the algorithm is uniformly asymptotically stable, irrespective of the x's. We note that the first derivative is smaller than unity in absolute value for any m, not just the fixed point.

What we should do now is either prove that the UAS property is also global, or that, if m(0) = \bar x then m(0) belongs to the neighborhood of attraction of m^*.

Source : Link , Question Author : Chris A. , Answer Author : Alecos Papadopoulos

Leave a Comment