{"title":"利用专家建议预测局部静态数据","authors":"V. V. V’yugin, V. G. Trunov, R. D. Zukhba","doi":"10.1134/s0032946024010058","DOIUrl":null,"url":null,"abstract":"<p>We address the lifelong machine learning problem. Within the game-theoretic approach, in the calculation of the next prediction we use no assumptions on the stochastic nature of a source that generates the data flow: the source can be either analog, or algorithmic, or probabilistic; its parameters can change at random times; when constructing a prediction model, only structural assumptions are used about the nature of data generation. We present an online forecasting algorithm for a locally stationary time series. We also obtain an estimate for the efficiency of the proposed algorithm. The obtained estimates for the regret of the algorithm are illustrated by results of numerical experiments.</p>","PeriodicalId":54581,"journal":{"name":"Problems of Information Transmission","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of Locally Stationary Data Using Expert Advice\",\"authors\":\"V. V. V’yugin, V. G. Trunov, R. D. Zukhba\",\"doi\":\"10.1134/s0032946024010058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>We address the lifelong machine learning problem. Within the game-theoretic approach, in the calculation of the next prediction we use no assumptions on the stochastic nature of a source that generates the data flow: the source can be either analog, or algorithmic, or probabilistic; its parameters can change at random times; when constructing a prediction model, only structural assumptions are used about the nature of data generation. We present an online forecasting algorithm for a locally stationary time series. We also obtain an estimate for the efficiency of the proposed algorithm. The obtained estimates for the regret of the algorithm are illustrated by results of numerical experiments.</p>\",\"PeriodicalId\":54581,\"journal\":{\"name\":\"Problems of Information Transmission\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2024-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Problems of Information Transmission\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1134/s0032946024010058\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, THEORY & METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Problems of Information Transmission","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s0032946024010058","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
Prediction of Locally Stationary Data Using Expert Advice
We address the lifelong machine learning problem. Within the game-theoretic approach, in the calculation of the next prediction we use no assumptions on the stochastic nature of a source that generates the data flow: the source can be either analog, or algorithmic, or probabilistic; its parameters can change at random times; when constructing a prediction model, only structural assumptions are used about the nature of data generation. We present an online forecasting algorithm for a locally stationary time series. We also obtain an estimate for the efficiency of the proposed algorithm. The obtained estimates for the regret of the algorithm are illustrated by results of numerical experiments.
期刊介绍:
Problems of Information Transmission is of interest to researcher in all fields concerned with the research and development of communication systems. This quarterly journal features coverage of statistical information theory; coding theory and techniques; noisy channels; error detection and correction; signal detection, extraction, and analysis; analysis of communication networks; optimal processing and routing; the theory of random processes; and bionics.