Efficient Online Portfolio with Logarithmic Regret

Abstract

We study the decades-old problem of online portfolio management and propose the first algorithm with logarithmic regret that is not based on Cover's Universal Portfolio algorithm and admits much faster implementation. Specifically Universal Portfolio enjoys optimal regret $\mathcal{O}(N\ln T)$ for $N$ financial instruments over $T$ rounds, but requires log-concave sampling and has a large polynomial running time. Our algorithm, on the other hand, ensures a slightly larger but still logarithmic regret of $\mathcal{O}(N^2(\ln T{)}^4)$, and is based on the well-studied Online Mirror Descent framework with a novel regularizer that can be implemented via standard optimization methods in time $\mathcal{O}(T{N}^{2.5})$ per round. The regret of all other existing works is either polynomial in $T$ or has a potentially unbounded factor such as the inverse of the smallest price relative.

References in corpus (1)

• Corralling a Band of Bandit Algorithms

Cited by in corpus (5)

• An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays
• Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
• Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
• An Iterative Riccati Algorithm for Online Linear Quadratic Control
• On Confidence Sequences for Bounded Random Processes via Universal Gambling Strategies