To refer to this page use:
|Abstract:||We provide a general mechanism to design online learning algorithms based on a minimax analysis within a drifting-games framework. Different online learning settings (Hedge, multi-armed bandit problems and online convex optimization) are studied by converting into various kinds of drifting games. The original minimax analysis for drifting games is then used and generalized by applying a series of relaxations, starting from choosing a convex surrogate of the 0-1 loss function. With different choices of surrogates, we not only recover existing algorithms, but also propose new algorithms that are totally parameter-free and enjoy other useful properties. Moreover, our drifting-games framework naturally allows us to study high probability bounds without resorting to any concentration results, and also a generalized notion of regret that measures how good the algorithm is compared to all but the top small fraction of candidates. Finally, we translate our new Hedge algorithm into a new adaptive boosting algorithm that is computationally faster as shown in experiments, since it ignores a large number of examples on each round.|
|Citation:||Luo, Haipeng, Schapire, Robert E. (A Drifting-Games Analysis for Online Learning and Applications to Boosting|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Advances in Neural Information Processing Systems|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.