Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Wei, Han, Andi, Bai, Mingyuan, Zhou, Huanjian, Zhang, Qixin, Suzuki, Taiji, Fukumizu, Kenji
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
by: Bu, Dake, et al.
Published: (2025)

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models
by: Bu, Dake, et al.
Published: (2026)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
by: Zhang, Tongcheng, et al.
Published: (2026)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
by: Kim, Juno, et al.
Published: (2025)

Post-Training as Reweighting: A Stochastic View of Reasoning Trajectories in Language Models
by: Bu, Dake, et al.
Published: (2025)

Diffusion Boosted Trees
by: Han, Xizewen, et al.
Published: (2024)

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
by: Farghly, Tyler, et al.
Published: (2025)

Provable Acceleration for Diffusion Models under Minimal Assumptions
by: Li, Gen, et al.
Published: (2024)

Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
by: Chen, Tianyu, et al.
Published: (2024)

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
by: Bu, Dake, et al.
Published: (2024)

Refining Adaptive Zeroth-Order Optimization at Ease
by: Shu, Yao, et al.
Published: (2025)

Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimization
by: Zhou, Tailin, et al.
Published: (2025)

A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
by: Wachi, Akifumi, et al.
Published: (2026)

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
by: Li, Yibang, et al.
Published: (2026)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
by: Bu, Dake, et al.
Published: (2025)

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

Flow matching achieves almost minimax optimal convergence
by: Fukumizu, Kenji, et al.
Published: (2024)

Provable Training Data Identification for Large Language Models
by: Liu, Zhenlong, et al.
Published: (2025)

Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections
by: Loaiza-Ganem, Gabriel, et al.
Published: (2024)

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
by: Wakayama, Tomoya, et al.
Published: (2025)

Direct Distributional Optimization for Provable Alignment of Diffusion Models
by: Kawata, Ryotaro, et al.
Published: (2025)

Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
by: Tao, Lue, et al.
Published: (2023)

Preventing Model Collapse via Contraction-Conditioned Neural Filters
by: Han, Zongjian, et al.
Published: (2025)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
by: Huang, Huipeng, et al.
Published: (2025)

Provably Robust Bayesian Counterfactual Explanations under Model Changes
by: Duell, Jamie, et al.
Published: (2026)

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
by: Nishikawa, Naoki, et al.
Published: (2024)

Diffusion Models with Double Guidance: Generate with aggregated datasets
by: Yang, Yanfeng, et al.
Published: (2025)

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
by: Hu, Jerry Yao-Chieh, et al.
Published: (2024)

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
by: Zhang, Yi, et al.
Published: (2025)

Dominating vs. Dominated: Generative Collapse in Diffusion Models
by: Jeong, Hayeon, et al.
Published: (2025)

LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations
by: Xiao, Qixin, et al.
Published: (2026)

Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond
by: Cao, Yang, et al.
Published: (2024)

On the Provable Performance Guarantee of Efficient Reasoning Models
by: Zeng, Hao, et al.
Published: (2025)

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
by: Han, Yujin, et al.
Published: (2025)

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
by: Bassan, Shahaf, et al.
Published: (2025)

Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
by: Park, Youngrok, et al.
Published: (2025)

Provable Zero-Shot Generalization in Offline Reinforcement Learning
by: Wang, Zhiyong, et al.
Published: (2025)

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
by: Lee, Kyowoon, et al.
Published: (2025)

Provable Benefits of In-Tool Learning for Large Language Models
by: Houliston, Sam, et al.
Published: (2025)

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
by: Yu, Xudong, et al.
Published: (2024)