3 papers
cs.LG2025
Efficient Over-parameterized Matrix Sensing from Noisy Measurements via Alternating Preconditioned Gradient Descent
Zhiyu Liu, Zhi Han, Yandong Tang +2
We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank is larger than the true rank of the target matrix $X_\star…
cs.LG2025
A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits
Jiannan Li, Yiyang Yang, Yao Wang +1
Modern decision-making scenarios often involve data that is both high-dimensional and rich in higher-order contextual information, where existing bandits algorithms fail to generat…
cs.GT2024
Optimal Mediation Mechanism in Bilateral Trade
Zhikang Fan, Weiran Shen, Shaojie Tang +1
We study the problem of designing revenue-maximizing mechanisms for a selfish mediator who facilitates trade between a buyer and a seller. We consider a setting where the mediator…