scientific article; zbMATH DE number 7626754

MaRDI QIDQ5053256zbMATH OpenFDO

Authors Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu

Publication date 6 December 2022

Full work available at URL https://arxiv.org/abs/2007.00590, https://jmlr.csail.mit.edu/papers/v22/21-0307.html

zbMATH Keywords

convergence ratedecentralized algorithmsdecentralized Bayesian inferenceHamiltonian Monte Carloheavy-ball methodLangevin dynamicsmomentum accelerationstochastic gradientWasserstein distance

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A class of Wasserstein metrics for probability distributions
• A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
• A First Course in Bayesian Statistical Methods
• Automated scalable Bayesian inference via Hilbert coresets
• Comparing consensus Monte Carlo strategies for distributed Bayesian computation
• Consistency and fluctuations for stochastic gradient Langevin dynamics
• Convergence of Langevin MCMC in KL-divergence
• Couplings and quantitative contraction rates for Langevin dynamics
• Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
• Deep learning: a Bayesian perspective
• Distributed Gradient Flow: Nonsmoothness, Nonconvexity, and Saddle Point Evasion
• Distributed Heavy-Ball: A Generalization and Acceleration of First-Order Methods With Gradient Tracking
• Distributed Subgradient Methods for Multi-Agent Optimization
• First-order methods of smooth convex optimization with inexact oracle
• Global Consensus Monte Carlo
• Global convergence of stochastic gradient Hamiltonian Monte Carlo for nonconvex stochastic optimization: nonasymptotic performance bounds and momentum-based acceleration
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• scientific article; zbMATH DE number 5454133 (Why is no real title available?)
• scientific article; zbMATH DE number 51132 (Why is no real title available?)
• scientific article; zbMATH DE number 964896 (Why is no real title available?)
• Introductory lectures on convex optimization. A basic course.
• Is there an analog of Nesterov acceleration for gradient-based MCMC?
• Linear time average consensus and distributed optimization on fixed graphs
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• On sampling from a log-concave density using kinetic Langevin diffusions
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• On Tests for Global Maximum of the Log-Likelihood Function
• On the convergence of decentralized gradient descent
• Online model selection based on the variational Bayes
• Optimal convergence rates for convex distributed optimization in networks
• Optimal Transport
• Parallel MCMC with generalized elliptical slice sampling
• Parallelizing stochastic gradient descent for least squares regression: mini-batching, averaging, and model misspecification
• Robust accelerated gradient methods for smooth strongly convex functions
• Robustness of Accelerated First-Order Algorithms for Strongly Convex Optimization Problems
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Stochastic Gradient-Based Distributed Bayesian Estimation in Cooperative Sensor Networks
• Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Cited in

(7)

• Hybrid deterministic-stochastic gradient Langevin dynamics for Bayesian learning
• The divide-and-conquer sequential Monte Carlo algorithm: theoretical properties and limit theorems
• Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
• Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning
• Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo
• Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory
• Wasserstein convergence guarantees for a general class of score-based generative models

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053256)