Optimal Convergence for Stochastic Optimization with Multiple Expectation Constraints

Kinjal Basu, Preetam Nandy

英文摘要：

In this paper, we focus on the problem of stochastic optimization where the objective function can be written as an expectation function over a closed convex set. We also consider multiple expectation constraints which restrict the domain of the problem. We extend the cooperative stochastic approximation algorithm from Lan and Zhou [2016] to solve the particular problem. We close the gaps in the previous analysis and provide a novel proof technique to show that our algorithm attains the optimal rate of convergence for both optimality gap and constraint violation when the functions are generally convex. We also compare our algorithm empirically to the state-of-the-art and show improved convergence in many situations.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Non parametric estimation of the structural expectation of a stochastic increasing function

This article introduces a non parametric warping model for functional data. When the outcome of an experiment is a sample of curves, data can be seen as realizations of a stochastic process, which takes into account the small variations between the different observed curves. The aim of this work is to define a mean pattern which represents the main behaviour of the set of all the realizations. So we define the structural expectation of the underlying stochastic function. Then we provide empirical estimators of this structural expectation and of each individual warping function. Consistency and…

2008-12-17math.STstat.TH

在对数Sobolev不等式下期望最大化算法的快速收敛性

Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequality

Department of Statistics, University of Warwick（沃里克大学统计系）

本文提出了一种基于对数Sobolev不等式分析EM算法的新框架，证明了其在有限样本下的误差界和指数收敛性，并扩展至多种EM变体。

2025-11-18cs.LGmath.OCmath.ST

Convergence of a Particle-based Approximation of the Block Online Expectation Maximization Algorithm

Online variants of the Expectation Maximization (EM) algorithm have recently been proposed to perform parameter inference with large data sets or data streams, in independent latent models and in hidden Markov models. Nevertheless, the convergence properties of these algorithms remain an open problem at least in the hidden Markov case. This contribution deals with a new online EM algorithm which updates the parameter at some deterministic times. Some convergence results have been derived even in general latent models such as hidden Markov models. These properties rely on the assumption that so…

2012-05-30math.STstat.TH

An Identity for Expectations and Characteristic Function of Matrix Variate Skew-normalDistribution with Applications to Associated Stochastic Orderings

We establish an identity for E f (Y) -E f (X), when X and Y both have matrix variateskew-normal distributions and the function f fulfills some weak conditions. Thecharacteristic function of matrix variate skew normal distribution is then derived. Finally,we make use of it to derive some necessary and sucient conditions for the comparisonof matrix variate skew-normal distributions under six di erent orders, such as usualstochastic order, convex order, increasing convex order, upper orthant order,directionally convex order and supermodular order.

2021-03-09math.STstat.TH

A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm

Institut de Mathématiques de Toulouse（图卢兹数学研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；Centre de Mathématiques Appliquées（应用数学中心）；Ecole Polytechnique（巴黎综合理工学院）；HSE University（高等经济大学）；The Chinese University of Hong Kong（香港中文大学）

The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations. This paper introduces a novel EM algorithm, called \texttt{SPIDER-EM}, for inference from a training set of size $n$, $n \gg 1$. At the core of our algorithm is an estimator of the full conditional expectation in the {\sf E}-step, adapted from the stochastic path-integrated differential estimator ({\tt SPIDER}) technique. We derive finite-time complexity bounds for smooth non-convex likelihood: we show that for convergence t…

2020-11-30cs.AIcs.LGmath.ST

Convergence and Convergence Rate of Stochastic Gradient Search in the Case of Multiple and Non-Isolated Extrema

The asymptotic behavior of stochastic gradient algorithms is studied. Relying on results from differential geometry (Lojasiewicz gradient inequality), the single limit-point convergence of the algorithm iterates is demonstrated and relatively tight bounds on the convergence rate are derived. In sharp contrast to the existing asymptotic results, the new results presented here allow the objective function to have multiple and non-isolated minima. The new results also offer new insights into the asymptotic properties of several classes of recursive algorithms which are routinely used in engineeri…

2013-09-17math.OCmath.STstat.TH

更多相关论文收起更多论文

Online Expectation Maximization based algorithms for inference in hidden Markov models

The Expectation Maximization (EM) algorithm is a versatile tool for model parameter estimation in latent data models. When processing large data sets or data stream however, EM becomes intractable since it requires the whole data set to be available at each iteration of the algorithm. In this contribution, a new generic online EM algorithm for model parameter inference in general Hidden Markov Model is proposed. This new algorithm updates the parameter estimate after a block of observations is processed (online). The convergence of this new algorithm is established, and the rate of convergence…

2012-10-16math.STstat.TH

Weak Convergence to Stochastic Integrals Driven by $α-$Stable Lévy Processes

We use the martingale convergence method to get the weak convergence theorem on general functionals of partial sums of independent heavy-tailed random variables. The limiting process is the stochastic integral driven by $α-$stable Lévy process. Our method is very powerful to obtain the limit behavior of heavy-tailed random variables.

2014-11-15math.STstat.TH

Convergent Stochastic Expectation Maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation

Estimation in the deformable template model is a big challenge in image analysis. The issue is to estimate an atlas of a population. This atlas contains a template and the corresponding geometrical variability of the observed shapes. The goal is to propose an accurate algorithm with low computational cost and with theoretical guaranties of relevance. This becomes very demanding when dealing with high dimensional data which is particularly the case of medical images. We propose to use an optimized Monte Carlo Markov Chain method into a stochastic Expectation Maximization algorithm in order to e…

2013-09-06math.STstat.TH

Strong Rate of Convergence for the Euler-Maruyama Approximation of Stochastic Differential Equations with Irregular Coefficients

We consider the Euler-Maruyama approximation for multi-dimensional stochastic differential equations with irregular coefficients. We provide the rate of strong convergence where the possibly discontinuous drift coefficient satisfies a one-sided Lipschitz condition and the diffusion coefficient is Hölder continuous.

2014-04-10math.PRmath.STstat.TH