no code implementations • ICLR 2022 • Tracy Ke, Longlin Wang
Lasso is a celebrated method for variable selection in linear models, but it faces challenges when the covariates are moderately or strongly correlated.
no code implementations • 16 May 2020 • Ningyuan Chen, Chun Wang, Longlin Wang
We show that our learning policy incurs a regret upper bound $\tilde{O}(\sqrt{T\sum_{k=1}^K T_k})$ where $T_k$ is the period of arm $k$.