Research map / Learning theory and algorithms / Sample complexity
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Orthogonal (off-support) score component is removed from the architecture's design of the score network; instead the encoder-decoder with shortcut -xb/h(t) is used | score network architecture · theory | score approximation error | No clear effect |
| Early stopping time t0 decreased | diffusion model distribution recovery · theory (Theorem on distribution estimation) | TV distance of latent distribution | Hurt |
| Early stopping time t0 decreased | diffusion model distribution recovery · theory (Theorem on distribution estimation) | W2 distance between P_t0^LD and P_z | Helped |
| Lipschitz-constrained score network (gamma, gamma_t) used in construction | score network · theory | score approximation error | No clear effect |
Closest papers by meaning
- Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models (NeurIPS 2024 · similarity 0.91)
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models (NeurIPS 2025 · similarity 0.90)
- Nearest Neighbour Score Estimators for Diffusion Generative Models (ICML 2024 · similarity 0.90)
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization (ICLR 2024 · similarity 0.89)
- Shallow diffusion networks provably learn hidden low-dimensional structure (ICLR 2025 · similarity 0.89)
- Training Diffusion-based Generative Models with Limited Data (ICML 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.