Fast and Robust Low-Rank Learning over Networks: A Decentralized Matrix Quantile Regression Approach
提出一种去中心化矩阵分位数回归方法，解决低秩学习中目标函数双重非光滑导致的收敛慢问题，算法简单且线性收敛，统计上达到近最优收敛率。
Decentralized low-rank learning is an active research domain with extensive practical applications. A common approach to producing low-rank and robust estimations is to employ a combination of the nonsmooth quantile regression loss and nuclear-norm regularizer. Nevertheless, directly applying existing techniques may result in slow convergence rates due to the doubly nonsmooth objective. To expedite the computation process, a decentralized surrogate matrix quantile regression method is proposed in this paper. The proposed algorithm has a simple implementation and can provably converge at a linear rate. Additionally, we provide a statistical guarantee that our estimate can achieve an almost optimal convergence rate, regardless of the number of nodes. Numerical simulations confirm the efficacy of our approach.