Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tang, Wenpin, Zhou, Fuzhong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Optimization and Control Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Regret of exploratory policy improvement and $q$-learning
di: Tang, Wenpin, et al.
Pubblicazione: (2024)

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
di: Huang, Yilie, et al.
Pubblicazione: (2026)

A unified perspective on fine-tuning and sampling with diffusion and flow models
di: Domingo-Enrich, Carles, et al.
Pubblicazione: (2026)

Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
di: Zhao, Hanyang, et al.
Pubblicazione: (2025)

An optimal control perspective on diffusion-based generative modeling
di: Berner, Julius, et al.
Pubblicazione: (2022)

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
di: Ke, Shuqi, et al.
Pubblicazione: (2024)

Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
di: Han, Yinbin, et al.
Pubblicazione: (2024)

Asymptotic regularity of a generalised stochastic Halpern scheme
di: Pischke, Nicholas, et al.
Pubblicazione: (2024)

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
di: Domingo-Enrich, Carles, et al.
Pubblicazione: (2024)

An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems
di: Zhang, Huiling, et al.
Pubblicazione: (2023)

Towards safe control parameter tuning in distributed multi-agent systems
di: Tokmak, Abdullah, et al.
Pubblicazione: (2025)

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
di: Sheng, Jiayuan, et al.
Pubblicazione: (2025)

What price to pay? Auto-tuning a building MPC controller for optimal economic cost
di: Yu, Jiarui, et al.
Pubblicazione: (2025)

Optimistic Online Non-stochastic Control via FTRL
di: Mhaisen, Naram, et al.
Pubblicazione: (2024)

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

Solving a class of stochastic optimal control problems by physics-informed neural networks
di: Jiao, Zhe, et al.
Pubblicazione: (2024)

A learning-based approach to stochastic optimal control under reach-avoid constraint
di: Ni, Tingting, et al.
Pubblicazione: (2024)

Gearing Gaussian process modeling and sequential design towards stochastic simulators
di: Binois, Mickael, et al.
Pubblicazione: (2024)

Iterative regularization in classification via hinge loss diagonal descent
di: Apidopoulos, Vassilis, et al.
Pubblicazione: (2022)

End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data
di: Chatzikiriakos, Nicolas, et al.
Pubblicazione: (2024)

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport
di: Zhang, Zhenyi, et al.
Pubblicazione: (2024)

Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition
di: Lee, Ching-pei, et al.
Pubblicazione: (2022)

Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
di: Zhou, Fuzhong, et al.
Pubblicazione: (2024)

Improved sampling via learned diffusions
di: Richter, Lorenz, et al.
Pubblicazione: (2023)

Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
di: Godichon-Baggioni, Antoine, et al.
Pubblicazione: (2024)

On subdifferential chain rule of matrix factorization and beyond
di: Guan, Jiewen, et al.
Pubblicazione: (2024)

Input layer regularization and automated regularization hyperparameter tuning for myelin water estimation using deep learning
di: Modi, Mirage, et al.
Pubblicazione: (2025)

Instance-optimal stochastic convex optimization: Can we improve upon sample-average and robust stochastic approximation?
di: Jiang, Liwei, et al.
Pubblicazione: (2026)

Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
di: Parfenov, Valery, et al.
Pubblicazione: (2026)

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
di: Wang, Zifan, et al.
Pubblicazione: (2026)

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
di: Marcotte, Sibylle, et al.
Pubblicazione: (2024)

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity
di: Zhu, Shuailong, et al.
Pubblicazione: (2025)

Generalized EXTRA stochastic gradient Langevin dynamics
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2024)

SGD with memory: fundamental properties and stochastic acceleration
di: Yarotsky, Dmitry, et al.
Pubblicazione: (2024)

A stochastic gradient method for trilevel optimization
di: Giovannelli, Tommaso, et al.
Pubblicazione: (2025)

Sum-of-norms regularized Nonnegative Matrix Factorization
di: Ang, Andersen, et al.
Pubblicazione: (2024)

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

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
di: Tsoy, Nikita, et al.
Pubblicazione: (2024)

Dealing with unbounded gradients in stochastic saddle-point optimization
di: Neu, Gergely, et al.
Pubblicazione: (2024)

New logarithmic step size for stochastic gradient descent
di: Shamaee, M. Soheil, et al.
Pubblicazione: (2024)