no code implementations • 8 Feb 2018 • Sevi Baltaoglu, Lang Tong, Qing Zhao
It is shown that the proposed algorithm converges, with an almost optimal convergence rate, to the global optimal corresponding to the case when the underlying price distribution is known.
no code implementations • NeurIPS 2017 • Sevi Baltaoglu, Lang Tong, Qing Zhao
By showing that the regret is lower bounded by $\Omega(\sqrt{T})$ for any strategy, we conclude that DPDS is order optimal up to a $\sqrt{\log{T}}$ term.