# Optimality of the Subgradient Algorithm in the Stochastic Setting

10 Sep 2019Daron AndersonDouglas Leith

We show that the Subgradient algorithm is universal for online learning on the simplex in the sense that it simultaneously achieves $O(\sqrt N)$ regret for adversarial costs and $O(1)$ pseudo-regret for i.i.d costs. To the best of our knowledge this is the first demonstration of a universal algorithm on the simplex that is not a variant of Hedge... (read more)

PDF Abstract

# Code Add Remove

No code implementations yet. Submit your code now