Preprint
Aug 2026
Mirror descent algorithms with logarithmic barriers
This work derives convergence guarantees for mirror descent and proximal mirror descent algorithms when a logarithmic barrier is used as a distance-generating function and shows that, in a specific setting, both methods enjoy an O(\log k / k) rate, which is also tight.
A. Marchi, Yura Malitsky, Adrien B. Taylor
· 0 citations