中文
相关论文

相关论文: Natural Langevin Dynamics for Neural Networks

200 篇论文

Stochastic Gradient Langevin Dynamics (SGLD) is a sampling scheme for Bayesian modeling adapted to large datasets and models. SGLD relies on the injection of Gaussian Noise at each step of a Stochastic Gradient Descent (SGD) update. In this…

机器学习 · 计算机科学 2018-06-11 Henri Palacci , Henry Hess

Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often…

机器学习 · 统计学 2018-11-27 Nicolas Brosse , Alain Durmus , Eric Moulines

Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based…

机器学习 · 计算机科学 2019-06-13 Chandrasekaran Anirudh Bhardwaj

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a…

机器学习 · 统计学 2022-05-24 Wei Deng , Guang Lin , Faming Liang

The Stochastic Gradient Langevin Dynamics (SGLD) are popularly used to approximate Bayesian posterior distributions in statistical learning procedures with large-scale data. As opposed to many usual Markov chain Monte Carlo (MCMC)…

机器学习 · 统计学 2024-04-30 Kexin Jin , Chenguang Liu , Jonas Latz

Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for…

机器学习 · 统计学 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin

Stochastic Gradient Langevin Dynamics (SGLD) is a powerful algorithm for optimizing a non-convex objective, where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global…

最优化与控制 · 数学 2020-06-04 Yuanhan Hu , Xiaoyu Wang , Xuefeng Gao , Mert Gurbuzbalaban , Lingjiong Zhu

In this work, we propose a Bayesian type sparse deep learning algorithm. The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network. The hierarchical Bayesian mixture will be trained using an…

数值分析 · 数学 2021-03-17 Yating Wang , Wei Deng , Lin Guang

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we…

计算金融 · 定量金融 2023-01-16 Pierre Bras , Gilles Pagès

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…

机器学习 · 计算机科学 2017-06-06 Maxim Raginsky , Alexander Rakhlin , Matus Telgarsky

Stochastic gradient MCMC methods, such as stochastic gradient Langevin dynamics (SGLD), employ fast but noisy gradient estimates to enable large-scale posterior sampling. Although we can easily extend SGLD to distributed settings, it…

机器学习 · 统计学 2021-06-16 Khaoula El Mekkaoui , Diego Mesquita , Paul Blomstedt , Samuel Kaski

Langevin algorithms are popular Markov Chain Monte Carlo methods for Bayesian learning, particularly when the aim is to sample from the posterior distribution of a parametric model, given the input data and the prior distribution over the…

机器学习 · 计算机科学 2025-10-28 Mert Gurbuzbalaban , Mohammad Rafiqul Islam , Xiaoyu Wang , Lingjiong Zhu

Stochastic gradient Langevin dynamics (SGLD) is a computationally efficient sampler for Bayesian posterior inference given a large scale dataset. Although SGLD is designed for unbounded random variables, many practical models incorporate…

机器学习 · 统计学 2019-06-21 Soma Yokoi , Takuma Otsuka , Issei Sato

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution. Our study uses a…

机器学习 · 计算机科学 2023-06-07 Shishir Adhikari , Alkan Kabakçıoğlu , Alexander Strang , Deniz Yuret , Michael Hinczewski

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…

机器学习 · 计算机科学 2024-07-08 August Y. Chen , Ayush Sekhari , Karthik Sridharan

In this paper we address the following question: Can we approximately sample from a Bayesian posterior distribution if we are only allowed to touch a small mini-batch of data-items for every sample we generate?. An algorithm based on the…

机器学习 · 计算机科学 2012-07-03 Sungjin Ahn , Anoop Korattikara , Max Welling

Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally infeasible. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem in three ways: it generates…

统计方法学 · 统计学 2015-09-22 Sebastian J. Vollmer , Konstantinos C. Zygalakis , and Yee Whye Teh

We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects appropriately scaled Gaussian noise to the update. We analyze…

机器学习 · 计算机科学 2018-04-10 Yuchen Zhang , Percy Liang , Moses Charikar

Flatness of the loss landscape has been widely studied as an important perspective for understanding the behavior and generalization of deep learning algorithms. Motivated by this view, we propose Flatness-Aware Stochastic Gradient Langevin…

机器学习 · 计算机科学 2026-05-28 Stefano Bruno , Youngsik Hwang , Jaehyeon An , Sotirios Sabanis , Dong-Young Lim

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

机器学习 · 计算机科学 2020-02-14 Yixuan Qiu , Xiao Wang
‹ 上一页 1 2 3 10 下一页 ›