Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation
cs.LG, cs.AI, stat.ML
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/Na-Li66/F-DDPM
Terminology
Sources
- Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
- Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
- Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
- Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
- Optimal Inference Schedules for Masked Diffusion Models
- Parallelism, critical windows, and separations among diffusion language models
- Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
- Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
- Convergence Analysis of Probability Flow ODE for Score-based Generative Models
- Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
- Instance-dependent Convergence Theory for Diffusion Models
- Optimal Convergence Analysis of DDPM for General Distributions
- Gotta Go Fast When Generating Data with Score-Based Models
- The Principles of Diffusion Models
- Provable Acceleration for Diffusion Models under Minimal Assumptions
- Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
- Accelerating Convergence of Score-Based Diffusion Models, Provably
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