Showing 2025Show all
3 papers · 1 filter
math.CA2025
A note on Cybenko's Universal Approximation Theorem
Kun Wang
In this short note, we point out a mistake in G.Cybenko's proof of his version of the universal approximation theorem which has been widely cited. This mistake might not be easily…
cs.LG2025
Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
Junyan Liu, Ziyun Chen, Kun Wang +2
We study the Pandora's Box problem in an online learning setting with semi-bandit feedback. In each round, the learner sequentially pays to open up to boxes with unknown reward…
cs.AI2025
Imitation Learning of Correlated Policies in Stackelberg Games
Kuang-Da Wang, Ping-Chun Hsieh, Wen-Chih Peng
Stackelberg games, widely applied in domains like economics and security, involve asymmetric interactions where a leader's strategy drives follower responses. Accurately modeling t…