A game of prediction with expert advice
Journal of Computer and System Sciences - Special issue on the eighth annual workshop on computational learning theory, July 5–8, 1995
An improvement on El-Yaniv-Fiat-Karp-Turpin's money-making bi-directional trading strategy
Information Processing Letters
Machine Learning - Special issue on context sensitivity and concept drift
Switching Between Two Universal Source Coding Algorithms
DCC '98 Proceedings of the Conference on Data Compression
Online trading algorithms and robust option pricing
Proceedings of the thirty-eighth annual ACM symposium on Theory of computing
| Hi-index | 5.23 |
We present two simple online two-way trading algorithms that exploit fluctuations in the unit price of an asset. Rather than analysing worst-case performance under some assumptions, we prove novel, unconditional performance bounds that are parameterised by a regularisation of the actual dynamics of the price of the asset. The mix algorithm processes T prices in O(T^2) time and O(T) space, but if the employed prior density is exponential, the time requirement reduces to O(T). The fix algorithm does the same in O(T) time and O(1) space, for any prior; its bound is slightly stronger than the bound for mix but only applies to a single regularisation that is determined by the algorithm. The result translates to the prediction with expert advice framework, and has applications in data compression and hypothesis testing.