Image de couverture de livre

Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tang, Wenpin, Zhou, Fuzhong
Format:	Preprint
Publié:	2024
Sujets:	Optimization and Control Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Regret of exploratory policy improvement and $q$-learning
par: Tang, Wenpin, et autres
Publié: (2024)

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
par: Huang, Yilie, et autres
Publié: (2026)

A unified perspective on fine-tuning and sampling with diffusion and flow models
par: Domingo-Enrich, Carles, et autres
Publié: (2026)

Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
par: Zhao, Hanyang, et autres
Publié: (2025)

An optimal control perspective on diffusion-based generative modeling
par: Berner, Julius, et autres
Publié: (2022)

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
par: Ke, Shuqi, et autres
Publié: (2024)

Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
par: Han, Yinbin, et autres
Publié: (2024)

Asymptotic regularity of a generalised stochastic Halpern scheme
par: Pischke, Nicholas, et autres
Publié: (2024)

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
par: Domingo-Enrich, Carles, et autres
Publié: (2024)

An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems
par: Zhang, Huiling, et autres
Publié: (2023)

Towards safe control parameter tuning in distributed multi-agent systems
par: Tokmak, Abdullah, et autres
Publié: (2025)

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
par: Sheng, Jiayuan, et autres
Publié: (2025)

What price to pay? Auto-tuning a building MPC controller for optimal economic cost
par: Yu, Jiarui, et autres
Publié: (2025)

Optimistic Online Non-stochastic Control via FTRL
par: Mhaisen, Naram, et autres
Publié: (2024)

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
par: Mou, Wenlong
Publié: (2025)

Solving a class of stochastic optimal control problems by physics-informed neural networks
par: Jiao, Zhe, et autres
Publié: (2024)

A learning-based approach to stochastic optimal control under reach-avoid constraint
par: Ni, Tingting, et autres
Publié: (2024)

Gearing Gaussian process modeling and sequential design towards stochastic simulators
par: Binois, Mickael, et autres
Publié: (2024)

Iterative regularization in classification via hinge loss diagonal descent
par: Apidopoulos, Vassilis, et autres
Publié: (2022)

End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data
par: Chatzikiriakos, Nicolas, et autres
Publié: (2024)

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport
par: Zhang, Zhenyi, et autres
Publié: (2024)

Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition
par: Lee, Ching-pei, et autres
Publié: (2022)

Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
par: Zhou, Fuzhong, et autres
Publié: (2024)

Improved sampling via learned diffusions
par: Richter, Lorenz, et autres
Publié: (2023)

Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
par: Godichon-Baggioni, Antoine, et autres
Publié: (2024)

On subdifferential chain rule of matrix factorization and beyond
par: Guan, Jiewen, et autres
Publié: (2024)

Input layer regularization and automated regularization hyperparameter tuning for myelin water estimation using deep learning
par: Modi, Mirage, et autres
Publié: (2025)

Instance-optimal stochastic convex optimization: Can we improve upon sample-average and robust stochastic approximation?
par: Jiang, Liwei, et autres
Publié: (2026)

Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
par: Parfenov, Valery, et autres
Publié: (2026)

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
par: Wang, Zifan, et autres
Publié: (2026)

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
par: Marcotte, Sibylle, et autres
Publié: (2024)

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity
par: Zhu, Shuailong, et autres
Publié: (2025)

Generalized EXTRA stochastic gradient Langevin dynamics
par: Gurbuzbalaban, Mert, et autres
Publié: (2024)

SGD with memory: fundamental properties and stochastic acceleration
par: Yarotsky, Dmitry, et autres
Publié: (2024)

A stochastic gradient method for trilevel optimization
par: Giovannelli, Tommaso, et autres
Publié: (2025)

Sum-of-norms regularized Nonnegative Matrix Factorization
par: Ang, Andersen, et autres
Publié: (2024)

Efficient model predictive control for nonlinear systems modelled by deep neural networks
par: Lan, Jianglin
Publié: (2024)

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
par: Tsoy, Nikita, et autres
Publié: (2024)

Dealing with unbounded gradients in stochastic saddle-point optimization
par: Neu, Gergely, et autres
Publié: (2024)

New logarithmic step size for stochastic gradient descent
par: Shamaee, M. Soheil, et autres
Publié: (2024)