English
Related papers

Related papers: A Convergence Analysis for A Class of Practical Va…

200 papers

Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stochastic counterparts with respect to the convergence rate,…

Machine Learning · Statistics 2016-03-23 Vatsal Shah , Megasthenis Asteris , Anastasios Kyrillidis , Sujay Sanghavi

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

In this work, minibatch MCMC sampling for feedforward neural networks is made more feasible. To this end, it is proposed to sample subgroups of parameters via a blocked Gibbs sampling scheme. By partitioning the parameter space, sampling is…

Machine Learning · Statistics 2023-07-25 Theodore Papamarkou

The resolution of many large-scale inverse problems using MCMC methods requires a step of drawing samples from a high dimensional Gaussian distribution. While direct Gaussian sampling techniques, such as those based on Cholesky…

Methodology · Statistics 2015-06-22 Clément Gilavert , Saïd Moussaoui , Jérôme Idier

The horseshoe prior is frequently employed in Bayesian analysis of high-dimensional models, and has been shown to achieve minimax optimal risk properties when the truth is sparse. While optimization-based algorithms for the extremely…

Computation · Statistics 2018-10-16 James E. Johndrow , Paulo Orenstein , Anirban Bhattacharya

Sampling from lattice Gaussian distribution has emerged as an important problem in coding, decoding and cryptography. In this paper, the classic Gibbs algorithm from Markov chain Monte Carlo (MCMC) methods is demonstrated to be…

Information Theory · Computer Science 2018-12-03 Zheng Wang

Markov Chain Monte Carlo (MCMC) methods such as Gibbs sampling are finding widespread use in applied statistics and machine learning. These often lead to difficult computational problems, which are increasingly being solved on parallel and…

Machine Learning · Statistics 2018-06-05 Alexander Terenin , Eric P. Xing

This work presents an efficient approach for accelerating multilevel Markov Chain Monte Carlo (MCMC) sampling for large-scale problems using low-fidelity machine learning models. While conventional techniques for large-scale Bayesian…

Machine Learning · Statistics 2024-05-21 Sohail Reddy , Hillary Fairbanks

We prove finite sample complexities for sequential Monte Carlo (SMC) algorithms which require only local mixing times of the associated Markov kernels. Our bounds are particularly useful when the target distribution is multimodal and global…

Computation · Statistics 2022-08-16 Joseph Mathews , Scott C. Schmidler

Random field Monte Carlo (MC) reliability analysis is a robust stochastic method to determine the probability of failure. This method, however, requires a large number of numerical simulations demanding high computational costs. This paper…

Machine Learning · Computer Science 2022-04-14 Mohammad Aminpour , Reza Alaie , Navid Kardani , Sara Moridpour , Majidreza Nazem

The increasing scale of data propels the popularity of leveraging parallelism to speed up the optimization. Minibatch stochastic gradient descent (minibatch SGD) and local SGD are two popular methods for parallel optimization. The existing…

Machine Learning · Computer Science 2025-10-14 Yunwen Lei , Tao Sun , Mingrui Liu

We present an original simulation-based method to estimate likelihood ratios efficiently for general state-space models. Our method relies on a novel use of the conditional Sequential Monte Carlo (cSMC) algorithm introduced in…

Methodology · Statistics 2018-09-10 Sinan Yıldırım , Christophe Andrieu , Arnaud Doucet

The stochastic gradient descent (SGD) algorithm has been widely used to optimize deep Cox neural network (Cox-NN) by updating model parameters using mini-batches of data. We show that SGD aims to optimize the average of mini-batch…

Machine Learning · Statistics 2026-04-16 Lang Zeng , Weijing Tang , Zhao Ren , Ying Ding

We study the computational complexity of Markov chain Monte Carlo (MCMC) methods for high-dimensional Bayesian linear regression under sparsity constraints. We first show that a Bayesian approach can achieve variable-selection consistency…

Statistics Theory · Mathematics 2015-06-01 Yun Yang , Martin J. Wainwright , Michael I. Jordan

The problem of optimising functions with intractable gradients frequently arise in machine learning and statistics, ranging from maximum marginal likelihood estimation procedures to fine-tuning of generative models. Stochastic approximation…

Machine Learning · Statistics 2026-01-30 James Cuin , Davide Carbone , Yanbo Tang , O. Deniz Akyildiz

In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a golden standard in the…

Optimization and Control · Mathematics 2017-09-20 Tomoya Murata , Taiji Suzuki

Interest is in evaluating, by Markov chain Monte Carlo (MCMC) simulation, the expected value of a function with respect to a, possibly unnormalized, probability distribution. A general purpose variance reduction technique for the MCMC…

Computation · Statistics 2012-09-19 Antonietta Mira , Reza Solgi , Daniele Imparato

Markov chain Monte Carlo (MCMC) is a powerful tool for sampling from complex probability distributions. Despite its versatility, MCMC often suffers from strong autocorrelation and the negative sign problem, leading to slowing down the…

Statistical Mechanics · Physics 2024-12-05 Synge Todo

We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated with a specific…

Machine Learning · Computer Science 2021-02-22 Robert Mansel Gower , Nicolas Loizou , Xun Qian , Alibek Sailanbayev , Egor Shulgin , Peter Richtarik

We introduce and characterise the performance of the Markov chain Monte Carlo (MCMC) inference method Prune Sampling for discrete and deterministic Bayesian networks (BNs). We developed a procedure to obtain the performance of a MCMC…

Computation · Statistics 2019-08-20 Frank Phillipson , Jurriaan Parie , Ron Weikamp