Tag
The author reflects on their regret of not consistently building their personal IP and shares insights from someone who switched to IP building in 2023 due to ChatGPT's rise, emphasizing the value of starting now.
This paper introduces THV-UCB, an algorithm for multi-objective bandit problems with slate selection, and establishes gap-free and gap-dependent regret bounds for hypervolume regret.
This paper introduces a normal-fan geometry for finite-horizon adversarial MDPs with fixed transitions, developing a face-crossing price that separates consequential from harmless non-stationarity. It shows that dynamic regret decomposes into intrinsic priced face motion plus within-face selection error.