4 citations · 8 across the 8 of their papers we have counts for
4 papers · 1 filter
Two Polyak-Type Step Sizes for Mirror Descent
Jun-Kai You, Yen-Huan Li
We propose two Polyak-type step sizes for mirror descent and prove their convergences for minimizing convex locally Lipschitz functions. Both step sizes, unlike the original Polyak…
A General Convergence Result for Mirror Descent with Armijo Line Search
Yen-Huan Li, Carlos A. Riofrio, Volkan Cevher
Existing convergence guarantees for the mirror descent algorithm require the objective function to have a bounded gradient or be smooth relative to a Legendre function. The bounded…
Convergence of the Exponentiated Gradient Method with Armijo Line Search
Yen-Huan Li, Volkan Cevher
Consider the problem of minimizing a convex differentiable function on the probability simplex, spectrahedron, or set of quantum density matrices. We prove that the exponentiated g…
A General Convergence Result for the Exponentiated Gradient Method
Yen-Huan Li, Volkan Cevher
The batch exponentiated gradient (EG) method provides a principled approach to convex smooth minimization on the probability simplex or the space of quantum density matrices. Howev…