arXiv:2608.22834 · v2

Mirror descent algorithms with logarithmic barriers

首次提交 2026-08-24 13:57

版本更新 2026-10-26 21:43

雷达观测 2026-10-29 00:35

摘要

We derive convergence guarantees for mirror descent and proximal mirror descent with a logarithmic barrier as the distance-generating function. When the solution lies on the boundary, the Bregman divergence blows up and classical guarantees become vacuous. While existing remedies recover $O(\log k/k)$ rates by adapting classical bounds, we propose a more direct route in which the Bregman distance to the solution never appears, and which achieves the same rate with constant stepsize. We also construct an example showing that this rate cannot be improved in general. Finally, we compare the proposed approach with interior-point methods.

作者备注：18 pages