Improved Random Features for Dot Product Kernels

被引:0
|
作者
Wacker, Jonas [1 ]
Kanagawa, Motonobu [1 ]
Filippone, Maurizio [2 ]
机构
[1] EURECOM, Data Sci Dept, Biot, France
[2] KAUST, Stat Program, Thuwal, Saudi Arabia
关键词
Random features; randomized sketches; dot product kernels; polynomial kernels; large scale learning;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Dot product kernels, such as polynomial and exponential (softmax) kernels, are among the most widely used kernels in machine learning, as they enable modeling the interactions between input features, which is crucial in applications like computer vision, natural language processing, and recommender systems. We make several novel contributions for improving the efficiency of random feature approximations for dot product kernels, to make these kernels more useful in large scale learning. First, we present a generalization of existing random feature approximations for polynomial kernels, such as Rademacher and Gaussian sketches and TensorSRHT, using complex-valued random features. We show empirically that the use of complex features can significantly reduce the variances of these approximations. Second, we provide a theoretical analysis for understanding the factors affecting the efficiency of various random feature approximations, by deriving closed-form expressions for their variances. These variance formulas elucidate conditions under which certain approximations (e.g., TensorSRHT) achieve lower variances than others (e.g., Rademacher sketches), and conditions under which the use of complex features leads to lower variances than real features. Third, by using these variance formulas, which can be evaluated in practice, we develop a data-driven optimization approach to improve random feature approximations for general dot product kernels, which is also applicable to the Gaussian kernel. We describe the improvements brought by these contributions with extensive experiments on a variety of tasks and datasets.
引用
收藏
页码:1 / 75
页数:75
相关论文
共 50 条
  • [31] Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere
    Azevedo, D.
    Menegatto, V. A.
    JOURNAL OF APPROXIMATION THEORY, 2014, 177 : 57 - 68
  • [32] A Limit Theorem for Scaled Eigenvectors of Random Dot Product Graphs
    Athreya, A.
    Priebe, C. E.
    Tang, M.
    Lyzinski, V.
    Marchette, D. J.
    Sussman, D. L.
    SANKHYA-SERIES A-MATHEMATICAL STATISTICS AND PROBABILITY, 2016, 78 (01): : 1 - 18
  • [33] A Limit Theorem for Scaled Eigenvectors of Random Dot Product Graphs
    Athreya A.
    Priebe C.E.
    Tang M.
    Lyzinski V.
    Marchette D.J.
    Sussman D.L.
    Sankhya A, 2016, 78 (1): : 1 - 18
  • [34] Maximum Likelihood Embedding of Logistic Random Dot Product Graphs
    O'Connor, Luke J.
    Medard, Muriel
    Feizi, Soheil
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 5289 - 5297
  • [35] Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels
    Luo, Qin
    Fang, Kun
    Yang, Jie
    Huang, Xiaolin
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [36] Support vector novelty detection with dot product kernels for non-spherical data
    Zhang, Li
    Zhou, Weida
    Lin, Ying
    Jiao, Licheng
    2008 INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, VOLS 1-4, 2008, : 41 - +
  • [37] Discovering the In-Memory Kernels of 3D Dot-Product Engines
    Rashed, Muhammad Rashedul Haq
    Jha, Sumit Kumar
    Ewetz, Rickard
    2023 28TH ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE, ASP-DAC, 2023, : 240 - 245
  • [38] RANDOM MATRIX-IMPROVED KERNELS FOR LARGE DIMENSIONAL SPECTRAL CLUSTERING
    Ali, Hafiz Tiomoko
    Kammoun, Abla
    Couillet, Romain
    2018 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), 2018, : 453 - 457
  • [39] Using random features of dot-matrix holograms for anticounterfeiting
    Yeh, Sheng Lih
    APPLIED OPTICS, 2006, 45 (16) : 3698 - 3703
  • [40] Exact counting of random height features of product surfaces
    Mohamed, M. A. S.
    JOURNAL OF TRIBOLOGY-TRANSACTIONS OF THE ASME, 2008, 130 (03):