Improved bounds on the sample complexity of learning

被引：96
|
作者：
Li, Y [1 ]
Long, PM
机构：
[1] Natl Univ Singapore, Dept Comp Sci, Singapore 117543, Singapore
[2] Lucent Technol, Bell Labs, Murray Hill, NJ 07974 USA
来源：
JOURNAL OF COMPUTER AND SYSTEM SCIENCES | 2001年 / 62卷 / 03期
关键词：
sample complexity; machine learning; empirical process theory; PAC learning; agnostic learning;
D O I：
10.1006/jcss.2000.1741
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
We present a new general upper bound on the number of examples required to estimate all of the expectations of a set of random variables uniformly well. The quality of the estimates is measured using a variant of the relative error proposed by Haussler and Pollard. We also show that our bound is within a constant factor of the best possible. Our upper bound implies improved bounds on the sample complexity of learning according to Haussler's decision theoretic model. (C) 2001 Academic Press.
引用
收藏
页码：516 / 527
页数：12
相关论文
共 50 条
  • [1] Improved bounds on the sample complexity of learning
    Li, Y
    Long, PM
    Srinivasan, A
    [J]. PROCEEDINGS OF THE ELEVENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, 2000, : 309 - 318
  • [2] Improved Sample-Complexity Bounds in Stochastic Optimization
    Baveja, Alok
    Chavan, Amit
    Nikiforov, Andrei
    Srinivasan, Aravind
    Xu, Pan
    [J]. OPERATIONS RESEARCH, 2023,
  • [3] SAMPLE COMPLEXITY BOUNDS ON DIFFERENTIALLY PRIVATE LEARNING VIA COMMUNICATION COMPLEXITY
    Feldman, Vitaly
    Xiao, David
    [J]. SIAM JOURNAL ON COMPUTING, 2015, 44 (06) : 1740 - 1764
  • [4] SAMPLE COMPLEXITY BOUNDS FOR DICTIONARY LEARNING OF TENSOR DATA
    Shakeri, Zahra
    Bajwa, Waheed U.
    Sarwate, Anand D.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 4501 - 4505
  • [5] IMPROVED SAMPLE COMPLEXITY-BOUNDS FOR PARAMETER-ESTIMATION
    TAKEUCHI, J
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1995, E78D (05) : 526 - 531
  • [6] Bounds on the sample complexity for private learning and private data release
    Beimel, Amos
    Brenner, Hai
    Kasiviswanathan, Shiva Prasad
    Nissim, Kobbi
    [J]. MACHINE LEARNING, 2014, 94 (03) : 401 - 437
  • [7] Bounds on the Sample Complexity for Private Learning and Private Data Release
    Beimel, Amos
    Kasiviswanathan, Shiva Prasad
    Nissim, Kobbi
    [J]. THEORY OF CRYPTOGRAPHY, PROCEEDINGS, 2010, 5978 : 437 - +
  • [8] Bounds on the sample complexity for private learning and private data release
    Amos Beimel
    Hai Brenner
    Shiva Prasad Kasiviswanathan
    Kobbi Nissim
    [J]. Machine Learning, 2014, 94 : 401 - 437
  • [9] Sample size lower bounds in PAC learning by Algorithmic Complexity Theory
    Apolloni, B
    Gentile, C
    [J]. THEORETICAL COMPUTER SCIENCE, 1998, 209 (1-2) : 141 - 162
  • [10] Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
    Mohammad Gheshlaghi Azar
    Rémi Munos
    Hilbert J. Kappen
    [J]. Machine Learning, 2013, 91 : 325 - 349
12345