Almost sure convergence rates for linear algorithms hk+1=hk+kχ1(bk−Akhk) are studied, where χ∈(0,1),
{Ak}k=1∞ are symmetric, positive semidefinite random matrices
and {bk}k=1∞ are random vectors. It is shown that ∣hn−A−1b∣=o(n−γ) a.s. for the γ∈[0,χ), positive definite
A and vector b such that nχ−γ1k=1∑n(Ak−A)→0 and nχ−γ1k=1∑n(bk−b)→0 a.s. When χ−γ∈(21,1), these assumptions are
implied by the Marcinkiewicz strong law of large numbers, which allows the
{Ak} and {bk} to have heavy-tails, long-range dependence or both.
Finally, corroborating experimental outcomes and decreasing-gain design
considerations are provided.