Fixed-point acceleration on Neural Wasserstein manifolds
cs.LG, math.OC
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Anderson Mixing in Bures Wasserstein Space of Gaussian Measures
- On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy
- TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision
- Evolutional Deep Neural Network
- Training generative neural networks via Maximum Mean Discrepancy optimization
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- An Introduction to Flow Matching and Diffusion Models
- Adam: A Method for Stochastic Optimization
- Riemannian Anderson Mixing Methods for Minimizing $C^2$-Functions on Riemannian Manifolds
- A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations
- Large-Scale Wasserstein Gradient Flows
- Propagating Surrogate Uncertainty in Bayesian Inverse Problems
- Optimal Transport for structured data with application on graphs
- Convergence Analysis for Restarted Anderson Mixing and Beyond
- Deep Tangent Bundle (DTB) method: a Deep Neural Network approach to compute solutions of PDES
- Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity
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