Skip to yearly menu bar Skip to main content


Poster

Discriminative State Space Models

Vitaly Kuznetsov · Mehryar Mohri

Pacific Ballroom #210

Keywords: [ Learning Theory ] [ Time Series Analysis ]


Abstract:

In this paper, we introduce and analyze Discriminative State-Space Models for forecasting non-stationary time series. We provide data-dependent generalization guarantees for learning these models based on the recently introduced notion of discrepancy. We provide an in-depth analysis of the complexity of such models. Finally, we also study the generalization guarantees for several structural risk minimization approaches to this problem and provide an efficient implementation for one of them which is based on a convex objective.

Live content is unavailable. Log in and register to view live content