The Elliptical Potential Lemma Revisited
arXiv:2010.10182v128 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental contribution aimed at researchers in online learning and bandit algorithms, offering improved theoretical tools.
The paper revisits the Elliptical Potential Lemma, a key result in online learning for linear stochastic bandits, by providing a new proof and perspectives to increase flexibility in potential types.
This note proposes a new proof and new perspectives on the so-called Elliptical Potential Lemma. This result is important in online learning, especially for linear stochastic bandits. The original proof of the result, however short and elegant, does not give much flexibility on the type of potentials considered and we believe that this new interpretation can be of interest for future research in this field.