Dependent relevance determination for smooth and structured sparse regression

被引:0
|
作者
Wu, Anqi [1 ]
Koyejo, Oluwasanmi [2 ]
Pillow, Jonathan [1 ]
机构
[1] Princeton Univ, Princeton Neurosci Inst, Princeton, NJ 08544 USA
[2] Univ Illinois, Dept Comp Sci, Beckman Inst Adv Sci & Technol, Urbana, IL 61801 USA
关键词
Bayesian nonparametric; Sparsity; Structure learning; Gaussian Process; fMRI; VARIABLE SELECTION; ALZHEIMERS-DISEASE; SHRINKAGE; THALAMUS; AREA; FMRI;
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
In many problem settings, parameter vectors are not merely sparse but dependent in such a way that non-zero coefficients tend to cluster together. We refer to this form of dependency as "region sparsity." Classical sparse regression methods, such as the lasso and automatic relevance determination (ARD), which model parameters as independent a priori, and therefore do not exploit such dependencies. Here we introduce a hierarchical model for smooth, region-sparse weight vectors and tensors in a linear regression setting. Our approach represents a hierarchical extension of the relevance determination framework, where we add a transformed Gaussian process to model the dependencies between the prior variances of regression weights. We combine this with a structured model of the prior variances of Fourier coefficients, which eliminates unnecessary high frequencies. The resulting prior encourages weights to be region-sparse in two different bases simultaneously. We develop Laplace approximation and Monte Carlo Markov Chain (MCMC) sampling to provide efficient inference for the posterior. Furthermore, a two-stage convex relaxation of the Laplace approximation approach is also provided to relax the inevitable non-convexity during the optimization. We finally show substantial improvements over comparable methods for both simulated and real datasets from brain imaging.
引用
收藏
页数:43
相关论文
共 50 条
  • [11] STRUCTURED, SPARSE REGRESSION WITH APPLICATION TO HIV DRUG RESISTANCE
    Percival, Daniel
    Roeder, Kathryn
    Rosenfeld, Roni
    Wasserman, Larry
    [J]. ANNALS OF APPLIED STATISTICS, 2011, 5 (2A): : 628 - 644
  • [12] Sparse smooth ridge regression method for supervised learning
    Ren, Weiya
    Li, Guohui
    [J]. Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology, 2015, 37 (06): : 121 - 128
  • [13] Correntropy-Based Logistic Regression With Automatic Relevance Determination for Robust Sparse Brain Activity Decoding
    Li, Yuanhao
    Chen, Badong
    Shi, Yuxi
    Yoshimura, Natsue
    Koike, Yasuharu
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2023, 70 (08) : 2416 - 2429
  • [14] Regression tracking with data relevance determination
    Patras, Ioannis
    Hancock, Edwin R.
    [J]. 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 2062 - +
  • [15] Tree-structured smooth transition regression models
    da Rosa, Joel Correa
    Veiga, Alvaro
    Medeiros, Marcelo C.
    [J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (05) : 2469 - 2488
  • [16] Structured Sparse Regression via Greedy Hard-thresholding
    Jain, Prateek
    Rao, Nikhil
    Dhillon, Inderjit
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
  • [17] SMOOTHING PROXIMAL GRADIENT METHOD FOR GENERAL STRUCTURED SPARSE REGRESSION
    Chen, Xi
    Lin, Qihang
    Kim, Seyoung
    Carbonell, Jaime G.
    Xing, Eric P.
    [J]. ANNALS OF APPLIED STATISTICS, 2012, 6 (02): : 719 - 752
  • [18] Slow Cortical Potential BCI Classification Using Sparse Variational Bayesian Logistic Regression with Automatic Relevance Determination
    Miladinovic, Aleksandar
    Ajcevic, Milos
    Battaglini, Piero Paolo
    Silveri, Giulia
    Ciacchi, Gaia
    Morra, Giulietta
    Jarmolowska, Joanna
    Accardo, Agostino
    [J]. XV MEDITERRANEAN CONFERENCE ON MEDICAL AND BIOLOGICAL ENGINEERING AND COMPUTING - MEDICON 2019, 2020, 76 : 1853 - 1860
  • [19] Double-structured sparse multitask regression with application of statistical downscaling
    Li, Yi
    Ding, A. Adam
    [J]. ENVIRONMETRICS, 2019, 30 (04)
  • [20] Sparse linear regression with structured priors and application to denoising of musical audio
    Fevotte, Cedric
    Torresani, Bruno
    Daudet, Laurent
    Godsill, Simon J.
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2008, 16 (01): : 174 - 185