Learning Theory and Algorithms for Forecasting Non-stationary Time Series
Annual Conference on Neural Information Processing Systems(2015)
摘要
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. We use our learning bounds to devise new algorithms for non-stationary time series forecasting for which we report some preliminary experimental results.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络