[edit]
Open Problem: Fast and Optimal Online Portfolio Selection
[edit]
Proceedings of Thirty Third Conference on Learning Theory, PMLR 125:38643869, 2020.
Abstract
Online portfolio selection has received much attention in the COLT community since its introduction by Cover, but all stateoftheart methods fall short in at least one of the following ways: they are either i) computationally infeasible; or ii) they do not guarantee optimal regret; or iii) they assume the gradients are bounded, which is unnecessary and cannot be guaranteed. We are interested in a natural followtheregularizedleader (FTRL) approach based on the log barrier regularizer, which is computationally feasible. The open problem we put before the community is to formally prove whether this approach achieves the optimal regret. Resolving this question will likely lead to new techniques to analyse FTRL algorithms. There are also interesting technical connections to selfconcordance, which has previously been used in the context of bandit convex optimization.
Related Material


