Learning in Structured Stackelberg Games

ORID XrKzHGg2jB · tags icml2026-repro paper-XrKzHGg2jB

#StatusPageArtifactClaim excerpt
1VERIFIED 2/201-stackelberg-littlestone-dimension-characterizesartifactThe Stackelberg-Littlestone (SL) dimension characterizes the optimal mistake bou…
2VERIFIED 2/202-algorithm-stackelberg-standard-optimal-algorithmartifactAlgorithm 1 (the Stackelberg Standard Optimal Algorithm) achieves a regret bound…
3VERIFIED 2/203-there-exist-stackelberg-game-instancesartifactThere exist Stackelberg game instances where the standard Littlestone dimension …
4VERIFIED 2/204-agnostic-online-setting-algorithm-regretartifactIn the agnostic online setting, the paper's algorithm achieves a regret bound of…
5VERIFIED 2/205-distributional-learning-contexts-stackelberg-natartifactFor distributional learning with contexts, the Stackelberg-Natarajan (SN) dimens…

Open logbook index · logbook.json