Image de couverture de livre

The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Johnston, Tim, Lytras, Iosif, Makras, Nikolaos, Sabanis, Sotirios
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Optimization and Control Probability Computation
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
par: Lim, Dong-Young, et autres
Publié: (2021)

Taming the Interacting Particle Langevin Algorithm: The Superlinear case
par: Johnston, Tim, et autres
Publié: (2024)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
par: Lytras, Iosif, et autres
Publié: (2025)

Flatness-Aware Stochastic Gradient Langevin Dynamics
par: Bruno, Stefano, et autres
Publié: (2025)

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients
par: Bruno, Stefano, et autres
Publié: (2025)

Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient
par: Lim, Dong-Young, et autres
Publié: (2022)

Tamed Langevin sampling under weaker conditions
par: Lytras, Iosif, et autres
Publié: (2024)

Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation
par: Akyildiz, Ö. Deniz, et autres
Publié: (2023)

On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
par: Bruno, Stefano, et autres
Publié: (2023)

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
par: Akyildiz, Ömer Deniz, et autres
Publié: (2020)

Error estimates for tamed Euler and Randomized Euler schemes for SDEs with locally Lipschitz drift with applications to non-logconcave sampling and optimization
par: Lytras, Iosif, et autres
Publié: (2026)

Contractive kinetic Langevin samplers beyond global Lipschitz continuity
par: Lytras, Iosif, et autres
Publié: (2025)

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
par: Sato, Kanji, et autres
Publié: (2022)

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
par: Chen, Yifan, et autres
Publié: (2024)

Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective
par: Srinivasan, Vishwak, et autres
Publié: (2025)

Weak Convergence Analysis of Online Neural Actor-Critic Algorithms
par: Lam, Samuel Chun-Hei, et autres
Publié: (2024)

Improved Approximation Algorithms for Orthogonally Constrained Problems Using Semidefinite Optimization
par: Cory-Wright, Ryan, et autres
Publié: (2025)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
par: Dang, Thanh, et autres
Publié: (2025)

Proximal Interacting Particle Langevin Algorithms
par: Encinar, Paula Cordero, et autres
Publié: (2024)

A Tamed Euler Scheme for SDEs with Non-Locally Integrable Drift Coefficient
par: Johnston, Tim, et autres
Publié: (2024)

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
par: Comte, Céline, et autres
Publié: (2023)

Why Smooth Stability Assumptions Fail for ReLU Learning
par: Katende, Ronald
Publié: (2025)

Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
par: Bhuyan, Neelkamal, et autres
Publié: (2023)

Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness
par: Small, Edward A., et autres
Publié: (2023)

Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need
par: Yang, Shangda, et autres
Publié: (2024)

Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
par: Narasimha, Dheeraj, et autres
Publié: (2025)

Non-convex entropic mean-field optimization via Best Response flow
par: Lascu, Razvan-Andrei, et autres
Publié: (2025)

ODE approximation for the Adam algorithm: General and overparametrized setting
par: Dereich, Steffen, et autres
Publié: (2025)

Admission Control of Quasi-Reversible Queueing Systems: Optimization and Reinforcement Learning
par: Comte, Céline, et autres
Publié: (2025)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
par: Kassing, Sebastian, et autres
Publié: (2025)

Representative Action Selection for Large Action Space Bandit Families
par: Zhou, Quan, et autres
Publié: (2025)

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers
par: Crafts, Evan Scope, et autres
Publié: (2025)

A stochastic gradient descent algorithm with random search directions
par: Gbaguidi, Eméric
Publié: (2025)

Reinforcement Learning with Random Time Horizons
par: Borrell, Enric Ribera, et autres
Publié: (2025)

Representative Action Selection for Large Action Space: From Bandits to MDPs
par: Zhou, Quan, et autres
Publié: (2025)

A Distributional View of High Dimensional Optimization
par: Benning, Felix
Publié: (2025)

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
par: Fouque, Jean-Pierre, et autres
Publié: (2025)

When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach
par: Zhao, Ruoning, et autres
Publié: (2025)

A Generalization Result for Convergence in Learning-to-Optimize
par: Sucker, Michael, et autres
Publié: (2024)

Properties of Discrete Sliced Wasserstein Losses
par: Tanguy, Eloi, et autres
Publié: (2023)