4 problems

Let $f$ be the saddle-point objective considered by ASLSQP, and call a critical point nonsaddle if it is not a locally optimal saddle point. An attractor of ASLSQP is a critical po…

Let $\eta$ denote the step size used by ASLSQP, and consider the convex--concave saddle-point setting in which the method is analyzed. Step-size bound conjecture. The upper bound o…

Consider general uniformly strongly convex-concave functions in both cases described by the source as situations … . Linear-rate conjecture. A refined analysis could yield a linear…

Let the SP-FW algorithm use step sizes $\gamma_t=\nicefrac{1}{(t+1)}$, and let it be applied to a uniformly strongly convex-concave objective function over a polytope. Hammond's co…