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. Our learning bounds guide the design of new algorithms for non-stationary time series forecasting for which we report several favorable experimental results.

中文翻译：

---

基于差异的预测非平稳时间序列的理论和算法

我们为非平稳非混合随机过程的一般场景提供了依赖于数据的学习界限。我们的学习保证表示为依赖于数据的顺序复杂性度量和可以在一些温和假设下从数据估计的差异度量。我们的学习界限指导了非平稳时间序列预测的新算法的设计，我们报告了几个有利的实验结果。