Flow Matching for Fast Posterior Sampling in Bayesian Inverse Problems

arXiv:2610.02377 · math.NA, cs.LG, cs.NA, stat.CO · Submitted 2026-10-01 · Read on arXiv

math.NA, cs.LG, cs.NA, stat.CO

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/EmoryMLIP/COT-Flow

Terminology

• Flow Matching — 1× in this paper · explained in 10 episodes
• Inverse Problem — 1× in this paper · explained in 2 episodes

Sources

• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
• Conditional score-based diffusion models for Bayesian inference in infinite dimensions
• How well do generative models solve inverse problems? A benchmark study
• Searching for Activation Functions
• Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans

Related papers

• Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
• A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
• Operator learning meets inverse problems: A probabilistic perspective
• Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
• Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
• Data-efficient Kernel Methods for Learning Hamiltonian Systems