Using and combining predictors that specialize
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Machine Learning - Special issue on context sensitivity and concept drift
Tracking a small set of experts by mixing past posteriors
The Journal of Machine Learning Research
Prediction, Learning, and Games
Prediction, Learning, and Games
Algorithms for portfolio management based on the Newton method
ICML '06 Proceedings of the 23rd international conference on Machine learning
Estimating the sortedness of a data stream
SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
From External to Internal Regret
The Journal of Machine Learning Research
Logarithmic regret algorithms for online convex optimization
COLT'06 Proceedings of the 19th annual conference on Learning Theory
λ-Perceptron: An adaptive classifier for data streams
Pattern Recognition
CORN: Correlation-driven nonparametric learning approach for portfolio selection
ACM Transactions on Intelligent Systems and Technology (TIST)
A closer look at adaptive regret
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Confidence Weighted Mean Reversion Strategy for Online Portfolio Selection
ACM Transactions on Knowledge Discovery from Data (TKDD)
A tale of two metrics: simultaneous bounds on competitiveness and regret
Proceedings of the ACM SIGMETRICS/international conference on Measurement and modeling of computer systems
Online portfolio selection: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in hindsight. Hence, regret minimizing algorithms tend to converge to the static best optimum, clearly a suboptimal behavior in changing environments. On the other hand, various metrics proposed to strengthen regret and allow for more dynamic algorithms produce inefficient algorithms. We propose a different performance metric which strengthens the standard metric of regret and measures performance with respect to a changing comparator. We then describe a series of data-streaming-based reductions which transform algorithms for minimizing (standard) regret into adaptive algorithms albeit incurring only poly-logarithmic computational overhead. Using this reduction, we obtain efficient low adaptive-regret algorithms for the problem of online convex optimization. This can be applied to various learning scenarios, i.e. online portfolio selection, for which we describe experimental results showing the advantage of adaptivity.