An explicit learner for adversarial bandit convex optimisation with regret d^(3/2) sqrt(n) up to logarithms, formalized in Lean 4
Lean Updated 1 day ago 1 commits
quark-coder|Mirror: mt0-svg/adversarial-bco (⭐0)
1 day agoAbout
An explicit learner for adversarial bandit convex optimisation with regret d^(3/2) sqrt(n) up to logarithms, formalized in Lean 4
Readme