English
Related papers

Related papers: Dale meets Langevin: A Multiplicative Denoising Di…

200 papers

Gradient optimization algorithms using epochs, that is those based on stochastic gradient descent without replacement (SGDo), are predominantly used to train machine learning models in practice. However, the mathematical theory of SGDo and…

Machine Learning · Computer Science 2025-12-05 Stefan Perko

Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC algorithms such as…

Machine Learning · Computer Science 2021-04-23 Zhisheng Xiao , Qing Yan , Yali Amit

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical mechanics, in…

Score-based generative models achieve state-of-the-art sampling performance by denoising a distribution perturbed by Gaussian noise. In this paper, we focus on a single deterministic denoising step, and compare the optimal denoiser for the…

Machine Learning · Computer Science 2026-03-18 Eliot Beyler , Francis Bach

Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the…

Machine Learning · Computer Science 2023-06-16 Chieh-Hsin Lai , Yuhta Takida , Naoki Murata , Toshimitsu Uesaka , Yuki Mitsufuji , Stefano Ermon

Dynamic mode decomposition (DMD) is an efficient tool for decomposing spatio-temporal data into a set of low-dimensional modes, yielding the oscillation frequencies and the growth rates of physically significant modes. In this paper, we…

Dynamical Systems · Mathematics 2023-02-21 Minwoo Lee , Jongho Park

A fundamental problem in Bayesian inference and statistical machine learning is to efficiently sample from multimodal distributions. Due to metastability, multimodal distributions are difficult to sample using standard Markov chain Monte…

Machine Learning · Statistics 2019-05-27 Yulong Lu , Jianfeng Lu , James Nolen

Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an…

Machine Learning · Statistics 2018-01-23 Stephan Mandt , Matthew D. Hoffman , David M. Blei

Diffusion models have achieved remarkable success in generating samples from unknown data distributions. Most popular stochastic differential equation-based diffusion models perturb the target distribution by adding Gaussian noise,…

Machine Learning · Statistics 2026-05-20 Wenpin Tang , Nizar Touzi , Zikun Zhang , Xun Yu Zhou

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…

Machine Learning · Statistics 2022-05-24 Wei Deng , Guang Lin , Faming Liang

We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust optimization (DRO)…

Machine Learning · Computer Science 2024-10-15 Ramnath Kumar , Kushal Majmundar , Dheeraj Nagaraj , Arun Sai Suggala

Stochastic Gradient Langevin Dynamics (SGLD) ensures strong guarantees with regards to convergence in measure for sampling log-concave posterior distributions by adding noise to stochastic gradient iterates. Given the size of many practical…

Machine Learning · Computer Science 2020-06-15 Vyacheslav Kungurtsev , Bapi Chatterjee , Dan Alistarh

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

We consider the distributed optimization problem where $n$ agents each possessing a local cost function, collaboratively minimize the average of the $n$ cost functions over a connected network. Assuming stochastic gradient information is…

Optimization and Control · Mathematics 2021-05-12 Kun Huang , Shi Pu

Score matching with Langevin dynamics (SMLD) method has been successfully applied to accelerated MRI. However, the hyperparameters in the sampling process require subtle tuning, otherwise the results can be severely corrupted by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Xiaoyu Qiao , Weisheng Li , Bin Xiao , Yuping Huang , Lijian Yang

Sampling from discrete distributions is a ubiquitous task in machine learning, recently revisited by the emergence of discrete diffusion models. While Langevin algorithms constitute the state of the art for continuous spaces, discrete…

Statistics Theory · Mathematics 2026-02-18 Armand Gissler , Saeed Saremi , Francis Bach

Distributed stochastic optimization algorithms can simultaneously process large-scale datasets, significantly accelerating model training. However, their effectiveness is often hindered by the sparsity of distributed networks and data…

Machine Learning · Computer Science 2025-02-14 Yuchen Hu , Xi Chen , Weidong Liu , Xiaojun Mao

We present a framework for adaptive-stepsize MCMC sampling based on time-rescaled Langevin dynamics, in which the stepsize variation is dynamically driven by an additional degree of freedom. Our approach augments the phase space by an…

Computation · Statistics 2025-05-27 Benedict Leimkuhler , René Lohmann , Peter Whalley

We consider stochastic approximations of sampling algorithms, such as Stochastic Gradient Langevin Dynamics (SGLD) and the Random Batch Method (RBM) for Interacting Particle Dynamcs (IPD). We observe that the noise introduced by the…

Probability · Mathematics 2023-10-10 Aniket Das , Dheeraj Nagaraj , Anant Raj

We present a theoretical analysis of some popular adaptive Stochastic Gradient Descent (SGD) methods in the small learning rate regime. Using the stochastic modified equations framework introduced by Li et al., we derive effective…

Machine Learning · Statistics 2025-09-29 Luca Callisti , Marco Romito , Francesco Triggiano
‹ Prev 1 4 5 6 7 8 10 Next ›