4 papers
On the resolution of -norm minimization via a two-metric adaptive projection method
Hanju Wu, Yue Xie
In this work, we propose an efficient two-metric adaptive projection method for solving the -norm minimization problem. Our approach is inspired by the two-metric projectio…
A Parameter-Free Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals
Qi Wang, Uday V. Shanbhag, Yue Xie
Most existing rate and complexity guarantees for stochastic gradient methods in -smooth settings mandates that such sequences be non-adaptive, non-increasing, and upper bounded…
Displacement-Sparse Neural Optimal Transport
Peter Chen, Yue Xie, Qingpeng Zhang
Optimal transport (OT) aims to find a map that transports mass from one probability measure to another while minimizing a cost function. Recently, neural OT solvers have gained…
A study on two-metric projection methods
Hanju Wu, Yue Xie
The two-metric projection method is a simple yet elegant algorithm proposed by Bertsekas in 1984 to address bound/box-constrained optimization problems. The algorithm's low per-ite…