Copertina

On the Interpolation Effect of Score Smoothing in Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Chen, Zhengdao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space
di: Chen, Zhengdao
Pubblicazione: (2023)

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
di: Attia, Amit, et al.
Pubblicazione: (2025)

Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
di: Li, Runjia, et al.
Pubblicazione: (2024)

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
di: Kolb, Chris, et al.
Pubblicazione: (2023)

Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control
di: Hua, Chengxiu, et al.
Pubblicazione: (2025)

Decentralized Stochastic Nonconvex Optimization under the Relaxed Smoothness
di: Luo, Luo, et al.
Pubblicazione: (2025)

Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
di: He, Qi, et al.
Pubblicazione: (2025)

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

On the Complexity of Decentralized Smooth Nonconvex Finite-Sum Optimization
di: Luo, Luo, et al.
Pubblicazione: (2022)

Stable Nonconvex-Nonconcave Training via Linear Interpolation
di: Pethick, Thomas, et al.
Pubblicazione: (2023)

Faster Gradient Methods for Highly-Smooth Stochastic Bilevel Optimization
di: Chen, Lesi, et al.
Pubblicazione: (2025)

Reward-Directed Score-Based Diffusion Models via q-Learning
di: Gao, Xuefeng, et al.
Pubblicazione: (2024)

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
di: Lai, Kuo-Wei, et al.
Pubblicazione: (2023)

Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation
di: Mishkin, Aaron, et al.
Pubblicazione: (2024)

Provable Adaptivity of Adam under Non-uniform Smoothness
di: Wang, Bohan, et al.
Pubblicazione: (2022)

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework
di: Nanda, Phalguni, et al.
Pubblicazione: (2026)

Score Matching Diffusion Based Feedback Control and Planning of Nonlinear Systems
di: Elamvazhuthi, Karthik, et al.
Pubblicazione: (2025)

Interpolation Conditions for Data Consistency and Prediction in Noisy Linear Systems
di: Vanelli, Martina, et al.
Pubblicazione: (2025)

Smooth Quasar-Convex Optimization with Constraints
di: Martínez-Rubio, David
Pubblicazione: (2025)

AdaGrad under Anisotropic Smoothness
di: Liu, Yuxing, et al.
Pubblicazione: (2024)

A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
di: Boursier, Etienne, et al.
Pubblicazione: (2025)

Adam-SHANG: A Convergent Adam-Type Method for Stochastic Smooth Convex Optimization
di: Yu, Yaxin, et al.
Pubblicazione: (2026)

Accelerating Convergence of Score-Based Diffusion Models, Provably
di: Li, Gen, et al.
Pubblicazione: (2024)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
di: Semenov, Andrei, et al.
Pubblicazione: (2025)

MGDA Converges under Generalized Smoothness, Provably
di: Zhang, Qi, et al.
Pubblicazione: (2024)

Directional Smoothness and Gradient Methods: Convergence and Adaptivity
di: Mishkin, Aaron, et al.
Pubblicazione: (2024)

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond
di: Wang, Bohan, et al.
Pubblicazione: (2024)

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
di: Cao, Daniel Yiming, et al.
Pubblicazione: (2025)

Deflation-Free Optimal Scoring
di: Afroz, Sharmin, et al.
Pubblicazione: (2026)

Probabilistic Smoothing with Ratio-Monotone Transforms for Global Optimization
di: Jang, Kukyoung, et al.
Pubblicazione: (2026)

Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization
di: Reifenstein, Sam, et al.
Pubblicazione: (2024)

Gradient-Variation Online Learning under Generalized Smoothness
di: Xie, Yan-Feng, et al.
Pubblicazione: (2024)

A Mirror Descent Perspective of Smoothed Sign Descent
di: Wang, Shuyang, et al.
Pubblicazione: (2024)

On Convergence of Incremental Gradient for Non-Convex Smooth Functions
di: Koloskova, Anastasia, et al.
Pubblicazione: (2023)

A Retrospective Approximation Approach for Smooth Stochastic Optimization
di: Newton, David, et al.
Pubblicazione: (2021)

Stochastic Non-Smooth Convex Optimization with Unbounded Gradients
di: Kovalev, Dmitry
Pubblicazione: (2026)

Diffusion Model for Data-Driven Black-Box Optimization
di: Li, Zihao, et al.
Pubblicazione: (2024)

Linearly Convergent Algorithms for Nonsmooth Problems with Unknown Smooth Pieces
di: Zhang, Zhe, et al.
Pubblicazione: (2025)

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
di: Zhao, Yuheng, et al.
Pubblicazione: (2025)

A Smoothing Newton Method for Rank-one Matrix Recovery
di: Maunu, Tyler, et al.
Pubblicazione: (2025)