English
Related papers

Related papers: Learning from non-irreducible Markov chains

200 papers

Recursive stochastic algorithms have gained significant attention in the recent past due to data driven applications. Examples include stochastic gradient descent for solving large-scale optimization problems and empirical dynamic…

Machine Learning · Computer Science 2020-07-27 Abhishek Gupta , Hao Chen , Jianzong Pi , Gaurav Tendolkar

The assumption that data samples are independently identically distributed is the backbone of many learning algorithms. Nevertheless, datasets often exhibit rich structure in practice, and we argue that there exist some unknown order within…

Machine Learning · Computer Science 2019-03-06 Yao-Hung Hubert Tsai , Han Zhao , Ruslan Salakhutdinov , Nebojsa Jojic

This work initiates a general study of learning and generalization without the i.i.d. assumption, starting from first principles. While the traditional approach to statistical learning theory typically relies on standard assumptions from…

Machine Learning · Statistics 2020-10-21 Steve Hanneke

Identifying a linear system model from data has wide applications in control theory. The existing work on finite sample analysis for linear system identification typically uses data from a single system trajectory under i.i.d random inputs,…

Systems and Control · Electrical Eng. & Systems 2023-09-19 Lei Xin , George Chiu , Shreyas Sundaram

We study the problem of learning Ising models satisfying Dobrushin's condition in the outlier-robust setting where a constant fraction of the samples are adversarially corrupted. Our main result is to provide the first computationally…

Machine Learning · Computer Science 2021-02-04 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart , Yuxin Sun

This article studies the convergence properties of trans-dimensional MCMC algorithms when the total number of models is finite. It is shown that, for reversible and some non-reversible trans-dimensional Markov chains, under mild conditions,…

Statistics Theory · Mathematics 2024-10-18 Qian Qin

Markov chain Monte Carlo algorithms are invaluable tools for exploring stationary properties of physical systems, especially in situations where direct sampling is unfeasible. Common implementations of Monte Carlo algorithms employ…

Statistical Mechanics · Physics 2016-04-27 Marija Vucelja

Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference. Despite its significance, theoretically there remain many important…

Machine Learning · Computer Science 2024-09-18 Mohammad Reza Karimi , Ya-Ping Hsieh , Andreas Krause

We propose an adaptive independent Metropolis--Hastings algorithm with the ability to learn from all previous proposals in the chain except the current location. It is an extension of the independent Metropolis--Hastings algorithm.…

Probability · Mathematics 2009-03-04 Lars Holden , Ragnar Hauge , Marit Holden

The consistency of the Bayesian estimation of a parameter is shown for a class of ergodic discrete Markov chains. J.L. Doob's method was used, offered earlier for the i.i.d. situation. The result may be useful in the reliability theory for…

Probability · Mathematics 2025-03-27 A. I. Nurieva , A. Yu. Veretennikov

This paper studies the theoretical underpinnings of machine learning of ergodic It\^o diffusions. The objective is to understand the convergence properties of the invariant statistics when the underlying system of stochastic differential…

Machine Learning · Computer Science 2021-10-04 He Zhang , John Harlim , Xiantao Li

In the paper, we study a new rate of convergence estimate for homogeneous discrete-time nonlinear Markov chains based on the Markov-Dobrushin condition. This result generalizes the convergence estimates for any positive number of transition…

Probability · Mathematics 2021-10-22 Aleksandr A. Shchegolev

Adaptive Markov chains are an important class of Monte Carlo methods for sampling from probability distributions. The time evolution of adaptive algorithms depends on past samples, and thus these algorithms are non-Markovian. Although there…

Probability · Mathematics 2014-10-02 Natesh S. Pillai , Aaron Smith

Stochastic gradient descent (SGD) is a popular algorithm for minimizing objective functions that arise in machine learning. For constant step-sized SGD, the iterates form a Markov chain on a general state space. Focusing on a class of…

Optimization and Control · Mathematics 2025-03-26 David Shirokoff , Philip Zaleski

This paper studies theory and inference related to a class of time series models that incorporates nonlinear dynamics. It is assumed that the observations follow a one-parameter exponential family of distributions given an accompanying…

Statistics Theory · Mathematics 2012-04-19 Richard A. Davis , Heng Liu

Markov chain Monte Carlo methods have become popular in statistics as versatile techniques to sample from complicated probability distributions. In this work, we propose a method to parameterize and train transition kernels of Markov chains…

Machine Learning · Computer Science 2024-06-05 Evgenii Egorov , Ricardo Valperga , Efstratios Gavves

Markov chain Monte Carlo is a class of algorithms for drawing Markovian samples from high-dimensional target densities to approximate the numerical integration associated with computing statistical expectation, especially in Bayesian…

Computation · Statistics 2018-03-28 Khoa T. Tran

Empirical likelihood is a powerful semi-parametric method increasingly investigated in the literature. However, most authors essentially focus on an i.i.d. setting. In the case of dependent data, the classical empirical likelihood method…

Statistics Theory · Mathematics 2011-02-17 Hugo Harari-Kermadec

Based on some recent work of the author on stochastic approximation in non-markovian environments, the situation when the driving random process is non-ergodic in addition to being non-markovian is considered. Using this, we propose an…

Machine Learning · Statistics 2026-03-24 Vivek Shripad Borkar

As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergence involve an…

Optimization and Control · Mathematics 2024-03-05 Ali Devran Kara , Serdar Yuksel