Imagen de Portada

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bruno, Stefano, Sabanis, Sotirios
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Optimization and Control Probability
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Flatness-Aware Stochastic Gradient Langevin Dynamics
por: Bruno, Stefano, et al.
Publicado: (2025)

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
por: Lim, Dong-Young, et al.
Publicado: (2021)

On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
por: Bruno, Stefano, et al.
Publicado: (2023)

The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions
por: Johnston, Tim, et al.
Publicado: (2025)

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

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
por: Akyildiz, Ömer Deniz, et al.
Publicado: (2020)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
por: Tanguy, Eloi
Publicado: (2023)

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
por: Altekrüger, Fabian, et al.
Publicado: (2023)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
por: Kassing, Sebastian, et al.
Publicado: (2025)

Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
por: Piening, Moritz, et al.
Publicado: (2026)

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
por: Sato, Kanji, et al.
Publicado: (2022)

Properties of Discrete Sliced Wasserstein Losses
por: Tanguy, Eloi, et al.
Publicado: (2023)

A Generalization Result for Convergence in Learning-to-Optimize
por: Sucker, Michael, et al.
Publicado: (2024)

Linear convergence of proximal descent schemes on the Wasserstein space
por: Lascu, Razvan-Andrei, et al.
Publicado: (2024)

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
por: Comte, Céline, et al.
Publicado: (2023)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
por: Dang, Thanh, et al.
Publicado: (2025)

Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow
por: Li, Qin, et al.
Publicado: (2024)

Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization
por: Dus, Mathias
Publicado: (2026)

Convergence rates for the Adam optimizer
por: Dereich, Steffen, et al.
Publicado: (2024)

Robust $Q$-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty
por: Neufeld, Ariel, et al.
Publicado: (2022)

Structure Matters: Dynamic Policy Gradient
por: Klein, Sara, et al.
Publicado: (2024)

Weak Convergence Analysis of Online Neural Actor-Critic Algorithms
por: Lam, Samuel Chun-Hei, et al.
Publicado: (2024)

Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA
por: Zhang, Yixuan, et al.
Publicado: (2024)

Set Invariance with Probability One for Controlled Diffusion: Score-based Approach
por: Wang, Wenqing, et al.
Publicado: (2025)

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
por: Fouque, Jean-Pierre, et al.
Publicado: (2025)

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
por: Hagemann, Paul, et al.
Publicado: (2023)

The geometry of financial institutions -- Wasserstein clustering of financial data
por: Riess, Lorenz, et al.
Publicado: (2023)

Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning
por: Srikant, R.
Publicado: (2024)

Wasserstein Contraction of Coordinate Ascent Variational Inference
por: Caprio, Rocco, et al.
Publicado: (2026)

Convergence rate of random scan Coordinate Ascent Variational Inference under log-concavity
por: Lavenant, Hugo, et al.
Publicado: (2024)

ODE approximation for the Adam algorithm: General and overparametrized setting
por: Dereich, Steffen, et al.
Publicado: (2025)

Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
por: Agrawal, Shubhada, et al.
Publicado: (2026)

Convergence rate of Tsallis entropic regularized optimal transport
por: Suguro, Takeshi, et al.
Publicado: (2023)

Algebraic Reduction of Hidden Markov Models
por: Grigoletto, Tommaso, et al.
Publicado: (2022)

Q-Learning under Finite Model Uncertainty
por: Sester, Julian, et al.
Publicado: (2024)

Convergence of linear programming hierarchies for Gibbs states of spin systems
por: Fawzi, Hamza, et al.
Publicado: (2025)

Model Predictive Control is Almost Optimal for Restless Bandit
por: Gast, Nicolas, et al.
Publicado: (2024)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
por: Lytras, Iosif, et al.
Publicado: (2025)

Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
por: Narasimha, Dheeraj, et al.
Publicado: (2025)

Convergence of coordinate ascent variational inference for log-concave measures via optimal transport
por: Arnese, Manuel, et al.
Publicado: (2024)