English
Related papers

Related papers: Near-Optimality of Contrastive Divergence Algorith…

200 papers

To fast approximate maximum likelihood estimators with massive data, this paper studies the Optimal Subsampling Method under the A-optimality Criterion (OSMAC) for generalized linear models. The consistency and asymptotic normality of the…

Methodology · Statistics 2021-06-15 Mingyao Ai , Jun Yu , Huiming Zhang , HaiYing Wang

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization…

Machine Learning · Computer Science 2024-12-10 Yao Lyu , Xiangteng Zhang , Shengbo Eben Li , Jingliang Duan , Letian Tao , Qing Xu , Lei He , Keqiang Li

We study the asymptotic stability of the semi-discrete (SD) numerical method for the approximation of stochastic differential equations. Recently, we examined the order of $\mathcal L^2$-convergence of the truncated SD method and showed…

Numerical Analysis · Mathematics 2020-08-10 Nikolaos Halidias , Ioannis S. Stamatiou

High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning algorithms with…

Optimization and Control · Mathematics 2021-06-08 Joseph E. Gaudio , Anuradha M. Annaswamy , José M. Moreu , Michael A. Bolender , Travis E. Gibson

We introduce a simple algorithm, True Asymptotic Natural Gradient Optimization (TANGO), that converges to a true natural gradient descent in the limit of small learning rates, without explicit Fisher matrix estimation. For quadratic models…

Machine Learning · Statistics 2017-12-25 Yann Ollivier

This paper introduces a quasi-likelihood ratio testing procedure for diffusion processes observed under nonsynchronous sampling schemes. High-frequency data, particularly in financial econometrics, are often recorded at irregular time…

Statistics Theory · Mathematics 2025-03-25 Teppei Ogihara , Futo Ueno

Sample complexity bounds are a common performance metric in the Reinforcement Learning literature. In the discounted cost, infinite horizon setting, all of the known bounds have a factor that is a polynomial in $1/(1-\gamma)$, where $\gamma…

Machine Learning · Computer Science 2020-07-09 Adithya M. Devraj , Sean P. Meyn

Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the…

Machine Learning · Computer Science 2021-03-01 Yanqiao Zhu , Yichen Xu , Feng Yu , Qiang Liu , Shu Wu , Liang Wang

The asymptotic optimality (a.o.) of various hyper-parameter estimators with different optimality criteria has been studied in the literature for regularized least squares regression problems. The estimators include e.g., the maximum…

Statistics Theory · Mathematics 2021-04-28 Biqiang Mu , Tianshi Chen , Lennart Ljung

Computing the approximate quantiles or ranks of a stream is a fundamental task in data monitoring. Given a stream of elements $x_1, x_2, \dots, x_n$ and a query $x$, a relative-error quantile estimation algorithm can estimate the rank of…

Data Structures and Algorithms · Computer Science 2024-11-05 Elena Gribelyuk , Pachara Sawettamalya , Hongxun Wu , Huacheng Yu

In this article we consider the graph alignment problem from the perspective of high-dimensional statistics: we aim to estimate an unknown permutation $\pi^*$ from the observation of two correlated random adjacency matrices $A_1$, $A_2$. We…

Probability · Mathematics 2025-10-30 Laurent Massoulié

Asymptotic spectral distribution (ASD) of the crosscorrelation matrix is investigated for a random spreading short/long-code asynchronous direct sequence-code division multiple access (DS-CDMA) system. The discrete-time decision statistics…

Information Theory · Computer Science 2008-10-06 Chien-Hwa Hwang

We consider the question of learning the natural parameters of a $k$ parameter minimal exponential family from i.i.d. samples in a computationally and statistically efficient manner. We focus on the setting where the support as well as the…

Machine Learning · Computer Science 2021-11-01 Abhin Shah , Devavrat Shah , Gregory W. Wornell

We present a technique for approximating generic normalization constants subject to constraints. The method is then applied to derive the exact asymptotics for the conditional normalization constant of constrained exponential random graphs.

Probability · Mathematics 2015-08-05 Mei Yin

This paper is concerned with minimizing the average of $n$ cost functions over a network in which agents may communicate and exchange information with each other. We consider the setting where only noisy gradient information is available.…

Optimization and Control · Mathematics 2021-02-02 Shi Pu , Alex Olshevsky , Ioannis Ch. Paschalidis

We study the problem of computationally efficient robust estimation of the covariance/scatter matrix of elliptical distributions -- that is, affine transformations of spherically symmetric distributions -- under the strong contamination…

Data Structures and Algorithms · Computer Science 2025-04-15 Gleb Novikov

We present an efficient algorithm for the min-max correlation clustering problem. The input is a complete graph where edges are labeled as either positive $(+)$ or negative $(-)$, and the objective is to find a clustering that minimizes the…

Data Structures and Algorithms · Computer Science 2025-02-19 Nairen Cao , Steven Roche , Hsin-Hao Su

We study the quadratic prediction error method -- i.e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition. While this method is known to asymptotically achieve…

Statistics Theory · Mathematics 2024-04-17 Charis Stamouli , Ingvar Ziemann , George J. Pappas

We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal…

Machine Learning · Computer Science 2017-12-13 Chuang Wang , Jonathan Mattingly , Yue M. Lu

We study the distributions of the LASSO, SCAD, and thresholding estimators, in finite samples and in the large-sample limit. The asymptotic distributions are derived for both the case where the estimators are tuned to perform consistent…

Statistics Theory · Mathematics 2009-09-07 Benedikt M. Potscher , Hannes Leeb