Hedge
PulseAugur coverage of Hedge — every cluster mentioning Hedge across labs, papers, and developer communities, ranked by signal.
-
New algorithm achieves optimal regret for online market making
Researchers have developed a new online learning algorithm for market making that achieves a high-probability regret bound of $\widetilde{\mathcal{O}}(\sqrt{T})$. This improves upon a previous guarantee of $\widetilde{\…
-
New H-MC caching policy offers improved regret guarantees over LRU/LFU
Researchers have developed a new caching policy called H-MC that aims to improve upon existing methods like LRU and LFU. Unlike previous policies such as LeCar and Cacheus, which can suffer from linear regret against ce…
-
Minimax Alternating Regret for Experts Problem and OCO Resolved · 2 sources tracked
Researchers have resolved the minimax regret rate for the Experts Problem and Online Convex Optimization (OCO). For the d-expert problem, the minimax alternating regret is shown to be $\Theta(\log d)$, independent of th…
-
New research details exact information accounting for Bayesian and multiplicative-weights updates
A new research paper introduces an exact information-accounting identity for Bayesian and multiplicative-weights updates. This identity reveals that the regret of any such update is directly related to the immediate pay…