An Improved Algorithm for Learning Drifting Discrete Distributions

被引:0
|
作者
Mazzetto, Alessio [1 ]
机构
[1] Brown Univ, Providence, RI 02912 USA
来源
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238 | 2024年 / 238卷
基金
美国国家科学基金会;
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
We present a new adaptive algorithm for learning discrete distributions under distribution drift. In this setting, we observe a sequence of independent samples from a discrete distribution that is changing over time, and the goal is to estimate the current distribution. Since we have access to only a single sample for each time step, a good estimation requires a careful choice of the number of past samples to use. To use more samples, we must resort to samples further in the past, and we incur a drift error due to the bias introduced by the change in distribution. On the other hand, if we use a small number of past samples, we incur a large statistical error as the estimation has a high variance. We present a novel adaptive algorithm that can solve this trade-off without any prior knowledge of the drift. Unlike previous adaptive results, our algorithm characterizes the statistical error using data-dependent bounds. This technicality enables us to overcome the limitations of the previous work that require a fixed finite support whose size is known in advance and that cannot change over time. Additionally, we can obtain tighter bounds depending on the complexity of the drifting distribution, and also consider distributions with infinite support.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] An improved learning algorithm for discrete Hopfield
    Li, R. (lirong0602@sina.com), 1600, Northeast University (29):
  • [2] On the complexity of learning from drifting distributions
    Barve, RD
    Long, PM
    INFORMATION AND COMPUTATION, 1997, 138 (02) : 170 - 193
  • [3] A new hybrid learning algorithm for drifting environments
    Kaikhah, Khosrow
    New Trends in Applied Artificial Intelligence, Proceedings, 2007, 4570 : 705 - 714
  • [4] An Algorithm for Quantization of Discrete Probability Distributions
    Reznik, Yuriy A.
    2011 DATA COMPRESSION CONFERENCE (DCC), 2011, : 333 - 342
  • [5] lp Testing and Learning of Discrete Distributions
    Waggoner, Bo
    PROCEEDINGS OF THE 6TH INNOVATIONS IN THEORETICAL COMPUTER SCIENCE (ITCS'15), 2015, : 346 - 355
  • [6] Instance Optimal Learning of Discrete Distributions
    Valiant, Gregory
    Valiant, Paul
    STOC'16: PROCEEDINGS OF THE 48TH ANNUAL ACM SIGACT SYMPOSIUM ON THEORY OF COMPUTING, 2016, : 142 - 155
  • [7] Learning discrete distributions with infinite support
    Cohen, Doron
    Kontorovich, Aryeh
    Wolfer, Geoffrey
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [8] A RECURSIVE ALGORITHM FOR CONVOLUTIONS OF DISCRETE UNIFORM DISTRIBUTIONS
    SUNDT, B
    INSURANCE MATHEMATICS & ECONOMICS, 1988, 7 (04): : 283 - 285
  • [9] An Improved Algorithm For Discrete Logarithm Problem
    Zhang, Jun
    Chen, LiQun
    2009 INTERNATIONAL CONFERENCE ON ENVIRONMENTAL SCIENCE AND INFORMATION APPLICATION TECHNOLOGY, VOL II, PROCEEDINGS, 2009, : 658 - 661
  • [10] A simple improved inferential method for some discrete distributions
    Cai, Y
    Krishnamoorthy, K
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2005, 48 (03) : 605 - 621