Discriminative state-space models

Vitaly Kuznetsov, Mehryar Mohri

Research output: Contribution to journalConference article

Abstract

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. 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.

Original languageEnglish (US)
Pages (from-to)5672-5680
Number of pages9
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - Jan 1 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

Fingerprint

Time series

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Discriminative state-space models. / Kuznetsov, Vitaly; Mohri, Mehryar.

In: Advances in Neural Information Processing Systems, Vol. 2017-December, 01.01.2017, p. 5672-5680.

Research output: Contribution to journalConference article

Kuznetsov, Vitaly ; Mohri, Mehryar. / Discriminative state-space models. In: Advances in Neural Information Processing Systems. 2017 ; Vol. 2017-December. pp. 5672-5680.
@article{eaccb377b20343448419e797e5f74f89,
title = "Discriminative state-space models",
abstract = "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. 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.",
author = "Vitaly Kuznetsov and Mehryar Mohri",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017-December",
pages = "5672--5680",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Discriminative state-space models

AU - Kuznetsov, Vitaly

AU - Mohri, Mehryar

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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. 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.

AB - 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. 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.

UR - http://www.scopus.com/inward/record.url?scp=85047021989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047021989&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85047021989

VL - 2017-December

SP - 5672

EP - 5680

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -