Theory and Algorithms for Forecasting Time Series

03/15/2018
by   Vitaly Kuznetsov, et al.
0

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 also also provide novel analysis of stable time series forecasting algorithm using this new notion of discrepancy that we introduce. We use our learning bounds to devise new algorithms for non-stationary time series forecasting for which we report some preliminary experimental results.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset