Hedge
A classical expert prediction algorithm in online learning based on exponentially weighted averaging, achieving a regret bound of O(√(T log N)) under oblivious input.
Timeline (last 90 days)
The classic Hedge algorithm achieves O(√(T log N)) regret under oblivious input, and this bound is tight in general.
A good online learning algorithm should guarantee that regret grows far below linearly with the number of rounds, with a typical target on the order of O(√T); Exponential Weights (Hedge) and UCB have been proven to achieve this guarantee.
All Facts (2)
The classic Hedge algorithm achieves O(√(T log N)) regret under oblivious input, and this bound is tight in general.
50%UnverifiedA good online learning algorithm should guarantee that regret grows far below linearly with the number of rounds, with a typical target on the order of O(√T); Exponential Weights (Hedge) and UCB have been proven to achieve this guarantee.
50%