English
Related papers

Related papers: Just Wing It: Near-Optimal Estimation of Missing M…

200 papers

Suppose we observe a trajectory of length $n$ from an exponentially $\alpha$-mixing stochastic process over a finite but potentially large state space. We consider the problem of estimating the probability mass placed by the stationary…

Machine Learning · Statistics 2025-06-09 Milind Nakul , Vidya Muthukumar , Ashwin Pananjady

The Good-Turing (GT) estimator for the missing mass (i.e., total probability of missing symbols) in $n$ samples is the number of symbols that appeared exactly once divided by $n$. For i.i.d. samples, the bias and squared-error risk of the…

Information Theory · Computer Science 2023-05-30 Prafulla Chandra , Andrew Thangaraj , Nived Rajaraman

Given $n$ samples from a population of individuals belonging to different types with unknown proportions, how do we estimate the probability of discovering a new type at the $(n+1)$-th draw? This is a classical problem in statistics,…

Statistics Theory · Mathematics 2018-06-27 Fadhel Ayed , Marco Battiston , Federico Camerlenghi , Stefano Favaro

We address the problem of estimating the mixing time $t_{\mathsf{mix}}$ of an arbitrary ergodic finite-state Markov chain from a single trajectory of length $m$. The reversible case was addressed by Hsu et al. [2019], who left the general…

Statistics Theory · Mathematics 2022-08-17 Geoffrey Wolfer , Aryeh Kontorovich

The spectral gap $\gamma$ of a finite, ergodic, and reversible Markov chain is an important parameter measuring the asymptotic rate of convergence. In applications, the transition matrix $P$ may be unknown, yet one sample of the chain up to…

Statistics Theory · Mathematics 2017-08-25 Daniel Hsu , Aryeh Kontorovich , David A. Levin , Yuval Peres , Csaba Szepesvári

The convergence rate of a Markov chain to its stationary distribution is typically assessed using the concept of total variation mixing time. However, this worst-case measure often yields pessimistic estimates and is challenging to infer…

Statistics Theory · Mathematics 2026-02-06 Geoffrey Wolfer , Pierre Alquier

Weighted empirical risk minimization is a common approach to prediction under distribution drift. This article studies its out-of-sample prediction error under nonstationarity. We provide a general decomposition of the excess risk into a…

Machine Learning · Statistics 2026-05-19 Tobias Brock , Thomas Nagler

The problem of missing mass in statistical inference (posed by McAllester and Ortiz, NIPS'02; most recently revisited by Changa and Thangaraj, ISIT'2019) seeks to estimate the weight of symbols that have not been sampled yet from a source.…

Probability · Mathematics 2020-01-15 Maciej Skorski

We study the estimation and concentration on its expectation of the probability to observe data further than a specified distance from a given iid sample in a metric space. The problem extends the classical problem of estimation of the…

Statistics Theory · Mathematics 2022-11-23 Andreas Maurer

This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time $t_{\text{mix}}$ of a finite reversible ergodic Markov chain at a prescribed confidence level. The interval is computed from…

Machine Learning · Computer Science 2015-11-04 Daniel Hsu , Aryeh Kontorovich , Csaba Szepesvári

We show that efficient approximate sampling algorithms, combined with a slow exponential time oracle for computing its output distribution, can be combined into constructing efficient perfect samplers, which sample exactly from a target…

Computational Complexity · Computer Science 2024-12-09 Andreas Göbel , Jingcheng Liu , Pasin Manurangsi , Marcus Pappik

The problem of estimating the missing mass or total probability of unseen elements in a sequence of $n$ random samples is considered under the squared error loss function. The worst-case risk of the popular Good-Turing estimator is shown to…

Information Theory · Computer Science 2017-05-16 Nikhilesh Rajaraman , Andrew Thangaraj , Ananda Theertha Suresh

We establish a simple variance inequality for U-statistics whose underlying sequence of random variables is an ergodic Markov Chain. The constants in this inequality are explicit and depend on computable bounds on the mixing rate of the…

Statistics Theory · Mathematics 2013-03-05 Gersende Fort , Eric Moulines , Pierre Priouret , Pierre Vandekerkhove

Feature allocation models generalize species sampling models by allowing every observation to belong to more than one species, now called features. Under the popular Bernoulli product model for feature allocation, given $n$ samples, we…

Statistics Theory · Mathematics 2020-09-22 Fadhel Ayed , Marco Battiston , Federico Camerlenghi , Stefano Favaro

We address the problem of estimating the mixing time of a Markov chain from a single trajectory of observations. Unlike most previous works which employed Hilbert space methods to estimate spectral gaps, we opt for an approach based on…

Probability · Mathematics 2023-09-13 Geoffrey Wolfer

Consider a discrete time, ergodic Markov chain with finite state space which is started from stationarity. Fill and Lyzinski (2014) showed that, in some cases, the hitting time for a given state may be represented as a sum of a geometric…

Probability · Mathematics 2018-12-20 Fraser Daly

We consider the problem of approximating the stationary distribution of an ergodic Markov chain given a set of sampled transitions. Classical simulation-based approaches assume access to the underlying process so that trajectories of…

Machine Learning · Computer Science 2020-03-03 Junfeng Wen , Bo Dai , Lihong Li , Dale Schuurmans

Imprecise continuous-time Markov chains are a robust type of continuous-time Markov chains that allow for partially specified time-dependent parameters. Computing inferences for them requires the solution of a non-linear differential…

Probability · Mathematics 2018-10-11 Alexander Erreygers , Jasper De Bock

We study continuous-time Markov chains on the non-negative integers under mild regularity conditions (in particular, the set of jump vectors is finite and both forward and backward jumps are possible). Based on the so-called flux balance…

Probability · Mathematics 2024-11-26 Mads Chr Hansen , Carsten Wiuf , Chuang Xu

The brilliant method due to Good and Turing allows for estimating objects not occurring in a sample. The problem, known under names "sample coverage" or "missing mass" goes back to their cryptographic work during WWII, but over years has…

Machine Learning · Statistics 2021-04-16 Maciej Skorski
‹ Prev 1 2 3 10 Next ›