Information theoretic limits of learning a sparse rule

被引:0
|
作者
Luneau, Clement [1 ]
Macris, Nicolas [1 ]
Barbier, Jean [2 ]
机构
[1] Ecole Polytech Fed Lausanne, Lausanne, Switzerland
[2] Abdus Salaam Int Ctr Theoret Phys, Trieste, Italy
关键词
MUTUAL INFORMATION; TIGHT BOUNDS; SHARP BOUNDS; CAPACITY; ERROR;
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
We consider generalized linear models in regimes where the number of nonzero components of the signal and accessible data points are sublinear with respect to the size of the signal. We prove a variational formula for the asymptotic mutual information per sample when the system size grows to infinity. This result allows us to derive an expression for the minimum mean-square error (MMSE) of the Bayesian estimator when the signal entries have a discrete distribution with finite support. We find that, for such signals and suitable vanishing scalings of the sparsity and sampling rate, the MMSE is nonincreasing piecewise constant. In specific instances the MMSE even displays an all-or-nothing phase transition, that is, the MMSE sharply jumps from its maximum value to zero at a critical sampling rate. The all-or-nothing phenomenon has previously been shown to occur in high-dimensional linear regression. Our analysis goes beyond the linear case and applies to learning the weights of a perceptron with general activation function in a teacher-student scenario. In particular, we discuss an all-or-nothing phenomenon for the generalization error with a sublinear set of training examples.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Information-Theoretic Limits of Algorithmic Noise Tolerance
    Seo, Daewon
    Varshney, Lav R.
    2016 IEEE INTERNATIONAL CONFERENCE ON REBOOTING COMPUTING (ICRC), 2016,
  • [32] Information-Theoretic Odometry Learning
    Sen Zhang
    Jing Zhang
    Dacheng Tao
    International Journal of Computer Vision, 2022, 130 : 2553 - 2570
  • [33] An Information Theoretic Approach of Designing Sparse Kernel Adaptive Filters
    Liu, Weifeng
    Park, Il
    Principe, Jose C.
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (12): : 1950 - 1961
  • [34] Information-theoretic competitive learning
    Kamimura, R
    IASTED: PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON MODELLING AND SIMULATION, 2003, : 359 - 365
  • [35] Information theoretic learning with adaptive kernels
    Singh, Abhishek
    Principe, Jose C.
    SIGNAL PROCESSING, 2011, 91 (02) : 203 - 213
  • [36] Information-Theoretic Odometry Learning
    Zhang, Sen
    Zhang, Jing
    Tao, Dacheng
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (11) : 2553 - 2570
  • [37] INFORMATION THEORETIC STRUCTURE LEARNING WITH CONFIDENCE
    Moon, Kevin R.
    Noshad, Morteza
    Sekeh, Salimeh Yasaei
    Hero, Alfred O., III
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 6095 - 6099
  • [38] Information theoretic clustering of sparse co-occurrence data
    Dhillon, IS
    Guan, YQ
    THIRD IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2003, : 517 - 520
  • [39] Tight information theoretic density bounds for sparse crossbar concentrators
    Gunduzhan, E
    Oruc, AY
    1998 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY - PROCEEDINGS, 1998, : 168 - 168
  • [40] PERFORMANCE LIMITS OF DICTIONARY LEARNING FOR SPARSE CODING
    Jung, Alexander
    Eldar, Yonina C.
    Goertz, Norbert
    2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 765 - 769