scientific article; zbMATH DE number 7626754

MaRDI QIDQ5053256

Yuanhan Hu, Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu

Publication date: 6 December 2022

Full work available at URL: https://arxiv.org/abs/2007.00590

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

convergence ratedecentralized algorithmsLangevin dynamicsWasserstein distancestochastic gradientHamiltonian Monte Carloheavy-ball methodmomentum accelerationdecentralized Bayesian inference

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• First-order methods of smooth convex optimization with inexact oracle
• A class of Wasserstein metrics for probability distributions
• Introductory lectures on convex optimization. A basic course.
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• When distributed computation is communication expensive
• Deep learning: a Bayesian perspective
• Comparing consensus Monte Carlo strategies for distributed Bayesian computation
• Is there an analog of Nesterov acceleration for gradient-based MCMC?
• Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
• On sampling from a log-concave density using kinetic Langevin diffusions
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Couplings and quantitative contraction rates for Langevin dynamics
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Online Model Selection Based on the Variational Bayes
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• On the Convergence of Decentralized Gradient Descent
• A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
• On Tests for Global Maximum of the Log-Likelihood Function
• A First Course in Bayesian Statistical Methods
• Linear Time Average Consensus and Distributed Optimization on Fixed Graphs
• Distributed Subgradient Methods for Multi-Agent Optimization
• Robustness of Accelerated First-Order Algorithms for Strongly Convex Optimization Problems
• Distributed Gradient Flow: Nonsmoothness, Nonconvexity, and Saddle Point Evasion
• Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration
• Global Consensus Monte Carlo
• Stochastic Gradient-Based Distributed Bayesian Estimation in Cooperative Sensor Networks
• Distributed Heavy-Ball: A Generalization and Acceleration of First-Order Methods With Gradient Tracking
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• Stochastic Processes and Applications
• Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
• Optimal Transport

This page was built for publication: