• Graduate Program
    • Why study Business Data Science?
    • Research Master
    • Admissions
    • Course Registration
    • Facilities
  • Summer School
  • Research
  • News
  • Events
    • Events Calendar
    • Events archive
    • Tinbergen Institute Lectures
    • Summer School
      • Deep Learning
      • Economics of Blockchain and Digital Currencies
      • Foundations of Machine Learning with Applications in Python
      • Machine Learning for Business
      • Marketing Research with Purpose
      • Sustainable Finance
      • Tuition Fees and Payment
      • Tinbergen Institute Summer School Program
    • Annual Tinbergen Institute Conference archive
  • Alumni
  • Magazine
Home | Events Archive | Robust Observation-Driven Models Using Proximal-Parameter Updates
Seminar

Robust Observation-Driven Models Using Proximal-Parameter Updates


  • Location
    University of Amsterdam, room E5.22
    Amsterdam
  • Date and time

    November 04, 2022
    12:30 - 13:30

Abstract
We propose a novel observation-driven modeling framework that allows for timevariation in the model’s parameters using a proximal-parameter (ProPar) update.The ProPar update is the solution to an optimization problem that maximizes thelogarithmic observation density with respect to the parameter, while penalizing thesquared distance of the parameter from its one-step-ahead prediction. The asso-ciated first-order condition has the form of an implicit stochastic-gradient update;replacing this implicit update with its explicit counterpart yields the popular classof score-driven models. Key advantages of the ProPar setup are stronger invertibil-ity properties (especially under model misspecification) as well as extended (globalrather than local) optimality properties. For the class of postulated observation den-sities whose logarithm is concave, ProPar’s robustness is evident from its (i) mutedresponse to large shocks in endogenous and exogenous variables, (ii) stability un-der poorly specified learning rates, and (iii) global contractivity towards a pseudo-truth—in all cases, even under model misspecification. We illustrate the generalapplicability and the practical usefulness of the ProPar framework for time-varyingregressions, volatility, and quantiles. Joint paper with Rutger-Jan Lange and Bram van Os.

Link to paper.