This talk is on stochastic subgradient mirror-descent method for solving
constrained convex minimization problems. In particular, a stochastic
subgradi-
ent mirror-descent method with weighted iterate-averaging is discussed and its
per-iterate convergence rate is analyzed. The novel part of the approach is in
the
choice of weights that are used to construct the averages. Through the use of
these weighted averages, we show that the known optimal rates can be obtained
with simpler algorithms than those currently existing in the literature.  The
stepsize choices that achieve the best rates are those proposed by Paul Tseng
for acceleration of proximal gradient methods.