论文标题
LRSVRG-IMC：一种基于SVRG的LowRank电感矩阵完成的算法
LRSVRG-IMC: An SVRG-Based Algorithm for LowRank Inductive Matrix Completion
论文作者
论文摘要
当前在物联网数据完成，推荐系统等中广泛使用低级电感矩阵完成（IMC），因为IMC中的侧面信息在减少样品点方面表现出巨大的潜力仍然是非convex溶液与IMC收敛的主要障碍。更重要的是，仅小心选择初始解决方案通常不会有助于删除鞍点。为了解决这个问题，我们提出了一种基于lrsvrg-imc的基于梯度的降低梯度算法。 LRSVRG-IMC可以在各种低级别和稀疏条件下以适当选择的初始输入从鞍点中逃脱。我们还证明，LRSVVRG-IMC既达到线性收敛速率又达到了近乎最佳的样本复杂性。 LRSVRG-IMC的优势和适用性通过合成数据集的实验验证。
Low-rank inductive matrix completion (IMC) is currently widely used in IoT data completion, recommendation systems, and so on, as the side information in IMC has demonstrated great potential in reducing sample point remains a major obstacle for the convergence of the nonconvex solutions to IMC. What's more, carefully choosing the initial solution alone does not usually help remove the saddle points. To address this problem, we propose a stocastic variance reduction gradient-based algorithm called LRSVRG-IMC. LRSVRG-IMC can escape from the saddle points under various low-rank and sparse conditions with a properly chosen initial input. We also prove that LRSVVRG-IMC achieves both a linear convergence rate and a near-optimal sample complexity. The superiority and applicability of LRSVRG-IMC are verified via experiments on synthetic datasets.
