Gaussian Process Neural Additive Models

被引:0
|
作者
Zhang, Wei [1 ]
Barr, Brian [2 ]
Paisley, John [1 ]
机构
[1] Columbia Univ, New York, NY 10025 USA
[2] Capital One, New York, NY USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required. The recent development of Neural Additive Models (NAMs) is a significant step in the direction of interpretable deep learning for tabular datasets. In this paper, we propose a new subclass of NAMs that use a single-layer neural network construction of the Gaussian process via random Fourier features, which we call Gaussian Process Neural Additive Models (GP-NAM). GP-NAMs have the advantage of a convex objective function and number of trainable parameters that grows linearly with feature dimensionality. It suffers no loss in performance compared to deeper NAM approaches because GPs are well-suited for learning complex non-parametric univariate functions. We demonstrate the performance of GP-NAM on several tabular datasets, showing that it achieves comparable or better performance in both classification and regression tasks with a large reduction in the number of parameters.
引用
下载
收藏
页码:16865 / 16872
页数:8
相关论文
共 50 条
  • [31] Gaussian Mixture Modeling with Gaussian Process Latent Variable Models
    Nickisch, Hannes
    Rasmussen, Carl Edward
    PATTERN RECOGNITION, 2010, 6376 : 272 - 282
  • [32] Multivariable generalized minimum variance control based on Artificial Neural Networks and Gaussian process models
    Sbarbaro, D
    Murray-Smith, R
    Valdes, A
    ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 2, 2004, 3174 : 52 - 58
  • [33] A Gaussian Process Model-Guided Surface Polishing Process in Additive Manufacturing
    Jin, Shilan
    Iquebal, Ashif
    Bukkapatnam, Satish
    Gaynor, Andrew
    Ding, Yu
    JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME, 2020, 142 (01):
  • [34] Neural Additive Models: Interpretable Machine Learning with Neural Nets
    Agarwal, Rishabh
    Melnick, Levi
    Frosst, Nicholas
    Zhang, Xuezhou
    Lengerich, Ben
    Caruana, Rich
    Hinton, Geoffrey E.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [35] Shared inverse Gaussian frailty models based on additive hazards
    Hanagal, David D.
    Pandey, Arvind
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2017, 46 (22) : 11143 - 11162
  • [36] Implementing Gaussian process inference with neural networks
    Frean, Marcus
    Lilley, Matt
    Boyle, Phillip
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2006, 16 (05) : 321 - 327
  • [37] Gaussian Process Neural Networks for Speech Recognition
    Lam, Max W. Y.
    Hu, Shoukang
    Xie, Xurong
    Liu, Shansong
    Yu, Jianwei
    Su, Rongfeng
    Liu, Xunying
    Meng, Helen
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1778 - 1782
  • [38] Contextual Gaussian Process Bandits with Neural Networks
    Zhang, Haoting
    He, Jinghai
    Righter, Rhonda
    Shen, Zuo-Jun Max
    Zheng, Zeyu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [39] Prediction With Approximated Gaussian Process Dynamical Models
    Beckers, Thomas
    Hirche, Sandra
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (12) : 6460 - 6473
  • [40] Identification of Gaussian Process State Space Models
    Eleftheriadis, Stefanos
    Nicholson, Thomas F. W.
    Deisenroth, Marc P.
    Hensman, James
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30