English
Related papers

Related papers: Generalized EXTRA stochastic gradient Langevin dyn…

200 papers

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its…

Machine Learning · Computer Science 2024-02-13 Anuraganand Sharma

Bayesian Neural Networks (BNNs) provide a promising framework for modeling predictive uncertainty and enhancing out-of-distribution robustness (OOD) by estimating the posterior distribution of network parameters. Stochastic Gradient Markov…

Machine Learning · Computer Science 2025-03-04 Hyunsu Kim , Giung Nam , Chulhee Yun , Hongseok Yang , Juho Lee

In this paper, we study the self-normalized Cram\'er-type moderate deviation of the empirical measure of the stochastic gradient Langevin dynamics (SGLD). Consequently, we also derive the Berry-Esseen bound for SGLD. Our approach is by…

Probability · Mathematics 2026-03-04 Hongsheng Dai , Xiequan Fan , Jianya Lu

We provide novel information-theoretic generalization bounds for stochastic gradient Langevin dynamics (SGLD) under the assumptions of smoothness and dissipativity, which are widely used in sampling and non-convex optimization studies. Our…

Machine Learning · Computer Science 2023-11-03 Futoshi Futami , Masahiro Fujisawa

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

Machine Learning · Computer Science 2023-05-30 Mingze Wang , Chao Ma

Score-based generative models (SGMs) have demonstrated remarkable synthesis quality. SGMs rely on a diffusion process that gradually perturbs the data towards a tractable distribution, while the generative model learns to denoise. The…

Machine Learning · Statistics 2022-03-28 Tim Dockhorn , Arash Vahdat , Karsten Kreis

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Discretizations of Langevin diffusions provide a powerful method for sampling and Bayesian inference. However, such discretizations require evaluation of the gradient of the potential function. In several real-world scenarios, obtaining…

Statistics Theory · Mathematics 2021-01-19 Abhishek Roy , Lingqing Shen , Krishnakumar Balasubramanian , Saeed Ghadimi

We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth…

Machine Learning · Statistics 2020-06-17 Adil Salim , Dmitry Kovalev , Peter Richtárik

This paper provides a finite-sample analysis of a passive stochastic gradient Langevin dynamics (PSGLD) algorithm. This algorithm is designed to achieve adaptive inverse reinforcement learning (IRL). Adaptive IRL aims to estimate the cost…

Machine Learning · Computer Science 2025-01-16 Luke Snow , Vikram Krishnamurthy

We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network…

Bayesian Federated Learning (BFL) enables uncertainty quantification and robust adaptation in distributed learning. In contrast to the frequentist approach, it estimates the posterior distribution of a global model, offering insights into…

Machine Learning · Computer Science 2025-04-23 Usevalad Milasheuski , Luca Barbieri , Sanaz Kianoush , Monica Nicoli , Stefano Savazzi

Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two consecutive phases…

Machine Learning · Computer Science 2017-10-11 Nanyang Ye , Zhanxing Zhu , Rafal K. Mantiuk

Machine learning models trained by different optimization algorithms under different data distributions can exhibit distinct generalization behaviors. In this paper, we analyze the generalization of models trained by noisy iterative…

Machine Learning · Statistics 2022-12-29 Hao Wang , Rui Gao , Flavio P. Calmon

We propose a decentralized learning algorithm over a general social network. The algorithm leaves the training data distributed on the mobile devices while utilizing a peer to peer model aggregation method. The proposed algorithm allows…

Machine Learning · Statistics 2019-05-28 Anusha Lalitha , Xinghan Wang , Osman Kilinc , Yongxi Lu , Tara Javidi , Farinaz Koushanfar

Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based…

Optimization and Control · Mathematics 2019-10-29 Sulaiman A. Alghunaim , Kun Yuan , Ali H. Sayed

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…

Machine Learning · Computer Science 2019-04-08 Craig Wilson , Yuheng Bu , Venugopal Veeravalli

Bayesian inference allows to obtain useful information on the parameters of models, either in computational statistics or more recently in the context of Bayesian Neural Networks. The computational cost of usual Monte Carlo methods for…

Machine Learning · Statistics 2023-03-03 Inass Sekkat , Gabriel Stoltz

In decentralized optimization, $m$ agents form a network and only communicate with their neighbors, which gives advantages in data ownership, privacy, and scalability. At the same time, decentralized stochastic gradient descent…

Optimization and Control · Mathematics 2022-12-13 Haishan Ye , Xiangyu Chang