Cost-augmented Schr"odinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Spectral analysis of the logit mapping and implications for stochastic user equilibrium algorithms
- Discrete Adjoint Schr\"odinger Bridge Sampler
- Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds
- Entropic Optimal Transport Problem with Convex Functional Cost
- Quantum-Enhanced Sampling of Schr"odinger Bridges
- Twisted Schr\"odinger Bridge Matching
- The BAR-SOT Method: Long-term Average Cost Control as Stochastic Optimal Self-Transport
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks