Online Learning with Feedback Graphs: Beyond Bandits
This work provides a foundational framework for understanding feedback in online learning, impacting researchers in machine learning and optimization by unifying and extending previous results.
The paper tackles the problem of online learning with feedback graphs, generalizing beyond bandits to cases where the player may not observe their own loss, and shows that the feedback graph's structure determines minimax regret rates, with specific bounds depending on graph properties like independence and domination numbers.
We study a general class of online learning problems where the feedback is specified by a graph. This class includes online prediction with expert advice and the multi-armed bandit problem, but also several learning problems where the online player does not necessarily observe his own loss. We analyze how the structure of the feedback graph controls the inherent difficulty of the induced $T$-round learning problem. Specifically, we show that any feedback graph belongs to one of three classes: strongly observable graphs, weakly observable graphs, and unobservable graphs. We prove that the first class induces learning problems with $\widetildeΘ(α^{1/2} T^{1/2})$ minimax regret, where $α$ is the independence number of the underlying graph; the second class induces problems with $\widetildeΘ(δ^{1/3}T^{2/3})$ minimax regret, where $δ$ is the domination number of a certain portion of the graph; and the third class induces problems with linear minimax regret. Our results subsume much of the previous work on learning with feedback graphs and reveal new connections to partial monitoring games. We also show how the regret is affected if the graphs are allowed to vary with time.