Denoising Is Stein: Moment Access and a Resource Hierarchy for Learning Hidden Structure in Diffusion Models
cs.LG, stat.ML
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Homotopy Analysis for Tensor PCA
- A theory of learning data statistics in diffusion models, from easy to hard
- Online stochastic gradient descent on non-convex losses from high-dimensional inference
- The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
- Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
- Computational-Statistical Gaps in Gaussian Single-Index Models
- The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
- Statistical Query Lower Bounds for Robust Estimation of High-dimensional Gaussians and Gaussian Mixtures
- SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions
- Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data
- Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
- Limitations of Lazy Training of Two-layers Neural Networks
- Linearized two-layers neural networks in high dimension
- An Alternative View: When Does SGD Escape Local Minima?
- Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
- Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
- An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings
- Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration
- Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis