一种非凸随机优化框架下的度量学习算法研究
(1.云南师范大学 数学学院,云南 昆明 650500;2.云南省现代分析数学及其应用重点实验室,云南 昆明 650500)
摘要
文章针对度量学习原凸问题的非凸重新表述,提出了一种带方差缩减策略的非凸随机优化算法(ML_NSVR),用于更高效地求解非凸度量学习问题。在适当的初始选择下,该算法在有限制的强凸条件下能够收敛,其收敛性得到了理论证明。数值实验验证了算法的有效性,为解决非凸度量学习问题提供了一种新的思路。同时,文章将所提算法与传统的随机梯度下降算法(SGD)和随机方差缩减梯度算法(SVRG)进行了优化效果对比。实验结果表明,ML_NSVR算法的效率更高。
关键词
随机优化;度量学习;方差缩减;非凸优化
参考文献
- [1] COLLET P,RENNARD J P. Stochastic Optimization Algorithms [M]//Intelligent information technologies:Concepts,methodologies,tools,and applications,2008:1121-1137.
- [2] LI B,JIANG W S. A Novel Stochastic Optimization Algorithm [J].IEEE Transactions on Systems,Man,and Cybernetics,Part B (Cybernetics),2000,30(1):193-198.
- [3] FEYZMAHDAVIAN H R,AYTEKIN A,JOHANSSON M. An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization [J].IEEE Transactions on Automatic Control,2016,61(12):3740-3754.
- [4] ZENG J S,MA K,YAO Y. Finding Global Optima in Nonconvex Stochastic Semidefinite Optimization with Variance Reduction [J/OL].arXiv:1802.06232 [math.OC].[2024-09-28].https://arxiv.org/abs/1802.06232.
- [5] KAYA M,BILGE H Ş. Deep Metric Learning: A Survey [J/OL].Symmetry,2019,11(9):1066[2024-09-28].https://doi.org/10.3390/sym11091066.
- [6] YANG L,JIN R. Distance Metric Learning: A Comprehensive Survey [J/OL].Michigan State Universiy,2006,2(2):4[2024-09-28].https://www.cs.cmu.edu/afs/cs.cmu.edu/Web/People/liuy/frame_survey_v2.
- [7] KULIS B. Metric Learning: A Survey [J].Foundations and Trends in Machine Learning,2012,5(4):287-364.
- [8] WANG R,WU X J,CHEN Z H,et al. SPD Manifold Deep Metric Learning for Image Set Classification [J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(7):8924-8938.
- [9] ZHANG Q,ZHOU Y,PRATER-BENNETTE A,et al. Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization [J/OL].arXiv:2404.01200 [stat.ML].[2024-09-28].https://arxiv.org/abs/2404.01200?context=stat.ML.
- [10] LI H C,QIAN J,TIAN Y,et al. Convex and Non-Convex Optimization under Generalized Smoothness [J/OL].arXiv:2306.01264 [math.OC].[2024-09-28].https://arxiv.org/abs/2306.01264.
- [11] XIE C H,LI C X,ZHANG C W,et al. Trust Region Methods for Nonconvex Stochastic Optimization Beyond Lipschitz Smoothness [J/OL].arXiv:2310.17319 [math.OC].[2024-09-28].https://arxiv.org/abs/2310.17319.
- [12] HU E L,KWOK J T. Low-Rank Matrix Learning Using Biconvex Surrogate inimization [J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(11):3517-3527.
- [13] NESTEROV Y. Smooth Minimization of Non-Smooth Functions [J].Mathematical programming,2005,103(1):127-152.
- [14] ERDOGDU M A,OZDAGLAR A,PARRILO P A,et al. Convergence Rate of Block-Coordinate Maximization Burer–Monteiro Method for Solving Large SDPs [J/OL].arXiv:1807.04428[math.OC].[2024-09-28].https://arxiv.org/abs/1807.04428?context=cs.LG.
基金项目
云南省现代分析数学及其应用重点实验室(202302AN360007);国家自然科学项目(62266055)
作者简介
徐忠城(1999—),男,汉族,云南曲靖人,硕士研究生,研究方向:机器学习。