English
Related papers

Related papers: Asymptotic Bias of Stochastic Gradient Search

200 papers

Approximate Bayesian computation (ABC) is a popular technique for approximating likelihoods and is often used in parameter estimation when the likelihood functions are analytically intractable. Although the use of ABC is widespread in many…

Statistics Theory · Mathematics 2011-03-29 Thomas A. Dean , Sumeetpal S. Singh , Ajay Jasra , Gareth W. Peters

We study asymptotic behavior of one-step $M$-estimators based on samples from arrays of not necessarily identically distributed random variables and representing explicit approximations to the corresponding consistent $M$-estimators. These…

Statistics Theory · Mathematics 2016-04-12 Yu. Yu. Linke

As saturated output observations are ubiquitous in practice, identifying stochastic systems with such nonlinear observations is a fundamental problem across various fields. This paper investigates the asymptotically efficient identification…

Machine Learning · Computer Science 2025-04-07 Lantian Zhang , Lei Guo

One of the primary challenges of system identification is determining how much data is necessary to adequately fit a model. Non-asymptotic characterizations of the performance of system identification methods provide this knowledge. Such…

Systems and Control · Electrical Eng. & Systems 2019-09-06 Bruce Lee , Andrew Lamperski

We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (DRM) of the cumulative reward in an episodic Markov decision…

Machine Learning · Computer Science 2024-02-06 Nithia Vijayan , Prashanth L. A

Linear optimization problems are investigated whose parameters are uncertain. We apply coherent distortion risk measures to capture the possible violation of a restriction. Each risk constraint induces an uncertainty set of coefficients,…

Methodology · Statistics 2017-12-18 Karl Mosler , Pavel Bazovkin

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the…

Machine Learning · Statistics 2020-07-29 Xiaoyu Li , Francesco Orabona

We study the distributional properties of the linear discriminant function under the assumption of normality by comparing two groups with the same covariance matrix but different mean vectors. A stochastic representation for the…

Statistics Theory · Mathematics 2017-05-09 Taras Bodnar , Stepan Mazur , Edward Ngailo , Nestor Parolya

Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a…

Optimization and Control · Mathematics 2018-09-13 Tao Sun , Yuejiao Sun , Wotao Yin

Online averaged stochastic gradient algorithms are more and more studied since (i) they can deal quickly with large sample taking values in high dimensional spaces, (ii) they enable to treat data sequentially, (iii) they are known to be…

Statistics Theory · Mathematics 2024-09-16 Antoine Godichon-Baggioni

Variational methods for parameter estimation are an active research area, potentially offering computationally tractable heuristics with theoretical performance bounds. We build on recent work that applies such methods to network data, and…

Statistics Theory · Mathematics 2013-10-30 Peter Bickel , David Choi , Xiangyu Chang , Hai Zhang

Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows…

Machine Learning · Computer Science 2017-06-06 Maxim Raginsky , Alexander Rakhlin , Matus Telgarsky

We study learning of probability distributions characterized by an unknown symmetry direction. Based on an entropic performance measure and the variational method of statistical mechanics we develop exact upper and lower bounds on the…

Disordered Systems and Neural Networks · Physics 2009-11-07 D. Herschkowitz , M. Opper

Reduced-rank regression is a dimensionality reduction method with many applications. The asymptotic theory for reduced rank estimators of parameter matrices in multivariate linear models has been studied extensively. In contrast, few…

Statistics Theory · Mathematics 2017-10-13 Efstathia Bura , Sabrina Duarte , Liliana Forzani , Ezequiel Smucler , Mariela Sued

A Bayesian non-parametric framework for studying time-to-event data is proposed, where the prior distribution is allowed to depend on an additional random source, and may update with the sample size. Such scenarios are natural, for…

Methodology · Statistics 2025-05-06 Martin Bladt , Jorge González Cázares

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

Asynchronous stochastic approximations (SAs) are an important class of model-free algorithms, tools and techniques that are popular in multi-agent and distributed control scenarios. To counter Bellman's curse of dimensionality, such…

Optimization and Control · Mathematics 2019-05-03 Arunselvan Ramaswamy , Shalabh Bhatnagar , Daniel E. Quevedo

We study the performance of a stochastic algorithm based on the power method that adaptively learns the large deviation functions characterizing the fluctuations of additive functionals of Markov processes, used in physics to model…

Statistical Mechanics · Physics 2023-03-30 Francesco Coghi , Hugo Touchette

In many statistical signal processing applications, the estimation of nuisance parameters and parameters of interest is strongly linked to the resulting performance. Generally, these applications deal with complex data. This paper focuses…

Applications · Statistics 2016-08-24 Melanie Mahot , Philippe Forster , Frederic Pascal , Jean-Philippe Ovarlez

A law of large numbers for the empirical distribution of parameters of a one-layer artificial neural networks with sparse connectivity is derived for a simultaneously increasing number of both, neurons and training iterations of the…

Disordered Systems and Neural Networks · Physics 2021-12-13 Christian Hirsch , Matthias Neumann , Volker Schmidt