English
Related papers

Related papers: Adaptive Stepsizing for Stochastic Gradient Langev…

200 papers

The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants…

Machine Learning · Computer Science 2025-09-22 Yuen Chen , Yian Wang , Hari Sundaram

Gaussian and discrete non-Gaussian spatial datasets are common across fields like public health, ecology, geosciences, and social sciences. Bayesian spatial generalized linear mixed models (SGLMMs) are a flexible class of models for…

Methodology · Statistics 2025-01-27 Jin Hyung Lee , Ben Seiyon Lee

We study the problem of non-convex optimization using Stochastic Gradient Langevin Dynamics (SGLD). SGLD is a natural and popular variation of stochastic gradient descent where at each step, appropriately scaled Gaussian noise is added. To…

Machine Learning · Computer Science 2024-07-08 August Y. Chen , Ayush Sekhari , Karthik Sridharan

In this paper, we study numerical approximations for stochastic differential equations (SDEs) that use adaptive step sizes. In particular, we consider a general setting where decisions to reduce step sizes are allowed to depend on the…

Numerical Analysis · Mathematics 2025-12-10 James Foster , Andraž Jelinčič

Mini-batch stochastic gradient descent (SGD) and variants thereof approximate the objective function's gradient with a small number of training examples, aka the batch size. Small batch sizes require little computation for each model update…

Machine Learning · Computer Science 2023-09-28 Scott Sievert , Shrey Shah

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this…

Machine Learning · Computer Science 2019-05-27 Shuai Zheng , James T. Kwok

Bayesian inference allows us to define a posterior distribution over the weights of a generic neural network (NN). Exact posteriors are usually intractable, in which case approximations can be employed. One such approximation - variational…

Machine Learning · Computer Science 2026-01-30 Andrew Millard , Joshua Murphy , Peter Green , Simon Maskell

Bayesian methods for learning Gaussian graphical models offer a principled framework for quantifying model uncertainty and incorporating prior knowledge. However, their scalability is constrained by the computational cost of jointly…

Methodology · Statistics 2025-08-28 Reza Mohammadi , Marit Schoonhoven , Lucas Vogels , S. Ilker Birbil

One of the major issues in stochastic gradient descent (SGD) methods is how to choose an appropriate step size while running the algorithm. Since the traditional line search technique does not apply for stochastic optimization algorithms,…

Optimization and Control · Mathematics 2016-05-24 Conghui Tan , Shiqian Ma , Yu-Hong Dai , Yuqiu Qian

Bayesian methods of sampling from a posterior distribution are becoming increasingly popular due to their ability to precisely display the uncertainty of a model fit. Classical methods based on iterative random sampling and posterior…

Machine Learning · Statistics 2022-11-04 Jacopo Guidolin , Vyacheslav Kungurtsev , Ondřej Kuželka

Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasingly popular in Bayesian learning due to its ability to deal with large data. A standard SG-MCMC algorithm simulates samples from a discretized-time Markov chain to…

Machine Learning · Statistics 2017-11-30 Changyou Chen , Ruiyi Zhang

We study a variation of vanilla stochastic gradient descent where the optimizer only has access to a Markovian sampling scheme. These schemes encompass applications that range from decentralized optimization with a random walker (token…

Optimization and Control · Mathematics 2023-06-26 Mathieu Even

Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of…

Machine Learning · Statistics 2019-09-18 Shen-Yi Zhao , Hao Gao , Wu-Jun Li

Model comparison for the purposes of selection, averaging and validation is a problem found throughout statistics. Within the Bayesian paradigm, these problems all require the calculation of the posterior probabilities of models within a…

Methodology · Statistics 2015-06-08 Yan Zhou , Adam M Johansen , John A D Aston

We present an optimizer which uses Bayesian optimization to tune the system parameters of distributed stochastic gradient descent (SGD). Given a specific context, our goal is to quickly find efficient configurations which appropriately…

Machine Learning · Statistics 2016-12-04 Valentin Dalibard , Michael Schaarschmidt , Eiko Yoneki

Stochastic gradient descent (SGD) is commonly used for optimization in large-scale machine learning problems. Langford et al. (2009) introduce a sparse online learning method to induce sparsity via truncated gradient. With high-dimensional…

Machine Learning · Statistics 2017-05-10 Yuting Ma , Tian Zheng

High-dimensional data are routinely collected in many areas. We are particularly interested in Bayesian classification models in which one or more variables are imbalanced. Current Markov chain Monte Carlo algorithms for posterior…

Methodology · Statistics 2024-01-15 Deborshee Sen , Matthias Sachs , Jianfeng Lu , David Dunson

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun

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

In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i.e. Schr\"odinger bridges). We advocate stochastic control as a finite time and low variance alternative to popular…