Estimating stationary mass, frequency by frequency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nakul, Milind, Muthukumar, Vidya, Pananjady, Ashwin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912416886947840
author Nakul, Milind
Muthukumar, Vidya
Pananjady, Ashwin
author_facet Nakul, Milind
Muthukumar, Vidya
Pananjady, Ashwin
contents Suppose we observe a trajectory of length $n$ from an exponentially $α$-mixing stochastic process over a finite but potentially large state space. We consider the problem of estimating the probability mass placed by the stationary distribution of any such process on elements that occur with a certain frequency in the observed sequence. We estimate this vector of probabilities in total variation distance, showing universal consistency in $n$ and recovering known results for i.i.d. sequences as special cases. Our proposed methodology -- implementable in linear time -- carefully combines the plug-in (or empirical) estimator with a recently-proposed modification of the Good--Turing estimator called WingIt, which was originally developed for Markovian sequences. En route to controlling the error of our estimator, we develop new performance bounds on WingIt and the plug-in estimator for exponentially $α$-mixing stochastic processes. Importantly, the extensively used method of Poissonization can no longer be applied in our non i.i.d. setting, and so we develop complementary tools -- including concentration inequalities for a natural self-normalized statistic of mixing sequences -- that may prove independently useful in the design and analysis of estimators for related problems. Simulation studies corroborate our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating stationary mass, frequency by frequency
Nakul, Milind
Muthukumar, Vidya
Pananjady, Ashwin
Machine Learning
Information Theory
Probability
Statistics Theory
Suppose we observe a trajectory of length $n$ from an exponentially $α$-mixing stochastic process over a finite but potentially large state space. We consider the problem of estimating the probability mass placed by the stationary distribution of any such process on elements that occur with a certain frequency in the observed sequence. We estimate this vector of probabilities in total variation distance, showing universal consistency in $n$ and recovering known results for i.i.d. sequences as special cases. Our proposed methodology -- implementable in linear time -- carefully combines the plug-in (or empirical) estimator with a recently-proposed modification of the Good--Turing estimator called WingIt, which was originally developed for Markovian sequences. En route to controlling the error of our estimator, we develop new performance bounds on WingIt and the plug-in estimator for exponentially $α$-mixing stochastic processes. Importantly, the extensively used method of Poissonization can no longer be applied in our non i.i.d. setting, and so we develop complementary tools -- including concentration inequalities for a natural self-normalized statistic of mixing sequences -- that may prove independently useful in the design and analysis of estimators for related problems. Simulation studies corroborate our theoretical findings.
title Estimating stationary mass, frequency by frequency
topic Machine Learning
Information Theory
Probability
Statistics Theory
url https://arxiv.org/abs/2503.12808