Professor Shulan Hu, a researcher of the base, has published a collaborative paper titled "The generalization ability of logistic regression with Markov sampling" in the Electronic Research Archive.
Abstract:
In the case of non-independent and identically distributed samples, we propose a new ueMC algorithm based on uniformly ergodic Markov samples, and study the generalization ability, the learning rate and convergence of the algorithm. We develop the ueMC algorithm to generate samples from given datasets, and present the numerical results for benchmark datasets. The numerical simulation shows that the logistic regression model with Markov sampling has better generalization ability on large training samples, and its performance is also better than that of classical machine learning algorithms, such as random forest and Adaboost.
Keywords:non-independent identically distributed samples, logistic regression model, uniformly ergodic Markov chain algorithm, generalization ability
Link:http://www.aimspress.com/article/doi/10.3934/era.2023267
Teacher profile
Shulan Hu, professor of Statistics and Mathematics School of Zhongnan University of Economics and Law, doctoral supervisor, Wen LAN Young Scholar, young teachers "research star". Director of Resources and Environment Branch of Chinese Field Statistics Society, Director of Big Data Branch and Director of Hubei Field Statistics Society. She is mainly engaged in the research of big data statistical algorithm theory and its application, econometric methods and financial applications. She has published more than 20 papers in Bernoulli, Statistics Sinica, Stochastic Processes and their Applications, Science in China, Science China Press and other authoritative academic journals at home and abroad. He wrote one academic monograph and edited Econometrics, the textbook of National Statistical Planning for the 14th Five-Year Plan. She has presided over and completed more than a dozen projects including National Natural Science Foundation Youth Project, National Social Science Foundation General Project, central university project, graduate quality course construction project, English course construction project, and horizontal project of enterprises and public institutions. She won the first and second-class mentoring student awards in various competitions, such as the National Market Survey Competition, the National Statistical Case Competition, the National Industrial and Economic Financial Big Data Modeling and Calculation Competition, and the American Mathematical Modeling Competition.