2 problems

Worst-case performance conjecture for gradient descent on linear-operator compositions
Let $g$ be a $mu_g$ -strongly convex and $L_g$ -smooth function, and let $M$ belong to the class of linear operators with singular values in $[mu_M,L_M]$ . Write…
openFrom papersgradient-method optimization worst-case-analysis
0 responses
8
Closed-form worst-case conjecture for gradient descent on $\mathcal{D}_{\mu_g}^{\mu_M}$
Closed-form worst-case conjecture. The worst-case performance satisfies
openFrom papersconvex-optimization gradient-method performance-estimation
0 responses
5

Worst-case performance conjecture for gradient descent on linear-operator compositions