Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Pathwise guessing in categorical time series with unbounded alphabets

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • معلومة اضافية
    • Contributors:
      Institut Polytechnique de Paris (IP Paris); Federal University of São Carlos (UFSCar); Instituto do Cérebro, UFRN, Natal (ICE)
    • بيانات النشر:
      CCSD
    • الموضوع:
      2025
    • نبذة مختصرة :
      The following learning problem arises naturally in various applications: Given a finite sample from a categorical or count time series, can we learn a function of the sample that (nearly) maximizes the probability of correctly guessing the values of a given portion of the data using the values from the remaining parts? Unlike the classical task of estimating conditional probabilities in a stochastic process, our approach avoids explicitly estimating these probabilities. We propose a non-parametric guessing function with a learning rate that is independent of the alphabet size. Our analysis focuses on a broad class of time series models that encompasses finite-order Markov chains, some hidden Markov chains, Poisson regression for count process, and one-dimensional Gibbs measures. Additionally, we establish a minimax lower bound for the rate of convergence of the risk associated with our guessing problem. This lower bound matches the upper bound achieved by our estimator up to a logarithmic factor, demonstrating its near-optimality.
    • الدخول الالكتروني :
      https://hal.science/hal-04881255
      https://hal.science/hal-04881255v1/document
      https://hal.science/hal-04881255v1/file/Guessing20240429_simplified.pdf
    • Rights:
      info:eu-repo/semantics/OpenAccess
    • الرقم المعرف:
      edsbas.A51D6454