哈工大马坚伟课题组学术报告

第2021-11-22期

南京大学

张绍群，本科和硕士阶段就读于四川大学数学学院，目前在南京大学计算机技术与科学系读博，师从周志华教授。主要研究兴趣是深度学习，神经计算，和时序分析。

Investigation of Long-term Memory without Periodogram and Gaussianity.

Mimicking and learning long-term memory is a fundamental problem in machine learning to sequential data. Despite the prominence of this issue, current treatments either remain largely limited to heuristic techniques or rely significantly on periodogram or Gaussianity assumptions. In this paper, we present the ApeRIodic SEmi-parametric (ARISE) process for investigating this issue. The ARISE process is formulated as an infinite-sum function of some known processes and employs the aperiodic spectrum estimation to determine the key hyper-parameters, thus possessing the power and potential of modelling the price data with long-term memory, non-stationarity, and aperiodic spectrum. We further theoretically show that the ARISE process has the mean-square convergence, consistency, and asymptotic normality without periodogram and Gaussianity assumptions. In practice, we provide three apposite ARISE applications: identifying the long-range dependency of real-world data, studying the long-term memorability of various machine-learning models, and developing a latent state-space model for inference and forecasting of time series. The numerical experiments confirm the superiority of our proposed approaches.

报告时间

2021年11月22日 北京时间19:30-20:00

腾讯会议

会议号：257 810 811