method · first seen 26 Oct 2026
best-of-both-worlds online learning
Bandit algorithms that achieve good regret under both adversarial and stochastic losses without knowing the environment type.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Three Worlds for the Price of a Logarithm: Baseline-Protected Best-of-Both-Worlds Combinatorial Semi-BanditsPapers · 26 Oct 2026 · Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis
Latest sources
- Three Worlds for the Price of a Logarithm: Baseline-Protected Best-of-Both-Worlds Combinatorial Semi-BanditsPapers · 26 Oct 2026 · Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis