English
Related papers

Related papers: On ergodicity of the SAGA-LD algorithm

200 papers

The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the…

Probability · Mathematics 2014-01-17 Andreas Eberle

In many modern applications, difficulty in evaluating the posterior density makes performing even a single MCMC step slow. This difficulty can be caused by intractable likelihood functions, but also appears for routine problems with large…

Statistics Theory · Mathematics 2015-08-25 Natesh S. Pillai , Aaron Smith

Recent years have witnessed exciting progress in the study of stochastic variance reduced gradient methods (e.g., SVRG, SAGA), their accelerated variants (e.g, Katyusha) and their extensions in many different settings (e.g., online, sparse,…

Machine Learning · Computer Science 2018-06-29 Kaiwen Zhou , Fanhua Shang , James Cheng

In real-world data, long-tailed data distribution is common, making it challenging for models trained on empirical risk minimisation to learn and classify tail classes effectively. While many studies have sought to improve long tail…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Ziheng Wang , Toni Lassila , Sharib Ali

Markov chain Monte Carlo methods provide an essential tool in statistics for sampling from complex probability distributions. While the standard approach to MCMC involves constructing discrete-time reversible Markov chains whose transition…

Computation · Statistics 2020-09-29 Joris Bierkens , Andrew Duncan

In many social, economical, biological and medical studies, one objective is to classify a subject into one of several classes based on a set of variables observed from the subject. Because the probability distribution of the variables is…

Statistics Theory · Mathematics 2011-05-19 Jun Shao , Yazhen Wang , Xinwei Deng , Sijian Wang

We investigate the equidistribution of the eigenfunctions on quantum graphs in the high-energy limit. Our main result is an estimate of the deviations from equidistribution for large well-connected graphs. We use an exact field-theoretic…

Chaotic Dynamics · Physics 2009-11-13 S. Gnutzmann , J. P. Keating , F. Piotet

Within the framework of the augmented Lagrangian (AL), we propose a novel distributed optimization method, termed Distributed Augmented Lagrangian Decomposition (DALD), and provide a rigorous convergence proof for its standard version. To…

Optimization and Control · Mathematics 2025-10-07 Wenyou Guo , Ting Qu , Hainan Huang , Yafeng Wei

This work explores a novel perspective on solving nonconvex and nonsmooth optimization problems by leveraging sampling based methods. Instead of treating the objective function purely through traditional (often deterministic) optimization…

Optimization and Control · Mathematics 2025-05-21 Nahom Seyoum , Haoxiang You

Standard MCMC methods can scale poorly to big data settings due to the need to evaluate the likelihood at each iteration. There have been a number of approximate MCMC algorithms that use sub-sampling ideas to reduce this computational…

Computation · Statistics 2020-09-29 Joris Bierkens , Paul Fearnhead , Gareth Roberts

Extrapolation methods use the last few iterates of an optimization algorithm to produce a better estimate of the optimum. They were shown to achieve optimal convergence rates in a deterministic setting using simple gradient iterates. Here,…

Optimization and Control · Mathematics 2017-08-04 Damien Scieur , Alexandre d'Aspremont , Francis Bach

Modern supervised learning techniques, particularly those using deep nets, involve fitting high dimensional labelled data sets with functions containing very large numbers of parameters. Much of this work is empirical. Interesting phenomena…

Machine Learning · Statistics 2018-05-30 Partha P Mitra

Pseudo-marginal Markov chain Monte Carlo methods for sampling from intractable distributions have gained recent interest and have been theoretically studied in considerable depth. Their main appeal is that they are exact, in the sense that…

Computation · Statistics 2015-03-25 Felipe J. Medina-Aguayo , Anthony Lee , Gareth O. Roberts

Since the paper of Kleinberg and Kleinberg, SODA'05, where it was proven that the preferential attachment random graph with degeneracy at least 3 does not obey the first order 0-1 law, no general methods were developed to study logical…

Probability · Mathematics 2023-11-01 Yury Malyshkin , Maksim Zhukovskii

The success of machine learning has resulted from its structured representation of data. Similar data have close internal representations as compressed codes for classification or emerged labels for clustering. We observe that the frequency…

Machine Learning · Computer Science 2022-04-13 Sungyeop Lee , Junghyo Jo

It is generally recognized that finite learning rate (LR), in contrast to infinitesimal LR, is important for good generalization in real-life deep nets. Most attempted explanations propose approximating finite-LR SGD with Ito Stochastic…

Machine Learning · Computer Science 2021-06-18 Zhiyuan Li , Sadhika Malladi , Sanjeev Arora

Piecewise deterministic Markov processes provide scalable methods for sampling from the posterior distributions in big data settings by admitting principled sub-sampling strategies that do not bias the output. An important example is the…

Computation · Statistics 2025-08-04 Sanket Agrawal , Joris Bierkens , Gareth O. Roberts

In this article, we discuss the optimal allocation problem in an experiment when a regression model is used for statistical analysis. Monotonic convergence for a general class of multiplicative algorithms for $D$-optimality has been…

Computation · Statistics 2013-10-28 Wei Gao , Ping Shing Chan , Hon Keung Tony Ng , Xiaolei Lu

This paper deals with Gibbs samplers that include high dimensional conditional Gaussian distributions. It proposes an efficient algorithm that avoids the high dimensional Gaussian sampling and relies on a random excursion along a small set…

Computation · Statistics 2016-04-20 Olivier Féron , François Orieux , Jean-François Giovannelli

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

Machine Learning · Statistics 2021-03-08 Nicole Mücke
‹ Prev 1 8 9 10 Next ›