DECO-EF achieves the first expected comparator-adaptive sublinear network-regret bounds for parameter-free decentralized online learning under compressed communication.
1, 2, 3 4
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
In the recent years, a number of parameter-free algorithms have been developed for online linear optimization over Hilbert spaces and for learning with expert advice. These algorithms achieve optimal regret bounds that depend on the unknown competitors, without having to tune the learning rates with oracle choices. We present a new intuitive framework to design parameter-free algorithms for \emph{both} online linear optimization over Hilbert spaces and for learning with expert advice, based on reductions to betting on outcomes of adversarial coins. We instantiate it using a betting algorithm based on the Krichevsky-Trofimov estimator. The resulting algorithms are simple, with no parameters to be tuned, and they improve or match previous results in terms of regret guarantee and per-round complexity.
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Shifted KT potentials equal a prior change in KT, and this removes the ln ln T factor from Squint's data-independent bound.
citing papers explorer
-
Decentralized Parameter-Free Online Learning with Compressed Gossip
DECO-EF achieves the first expected comparator-adaptive sublinear network-regret bounds for parameter-free decentralized online learning under compressed communication.
-
A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
Shifted KT potentials equal a prior change in KT, and this removes the ln ln T factor from Squint's data-independent bound.