Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
cs.LG, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- On the Convergence of SGD with Biased Gradients
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization
- Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
- Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains
- Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\L{}ojasiewicz Condition
- Fast Statistical Rates for Flow Matching without Curvature Assumptions
- Improving and generalizing flow-based generative models with minibatch optimal transport
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