paper-conference

The paper develops a theoretical and algorithmic foundation for solving the Schrödinger Bridge problem in discrete spaces using Iterative Markovian Fitting, introducing the CSBM algorithm and validating it with experiments on synthetic data and vector-quantized images.

We propose Electrostatic Field Matching (EFM), a novel method inspired by the physics of capacitors, which uses a neural network to learn electrostatic fields for generative modeling and distribution transfer.

We introduce a novel distillation technique for diffusion bridge models (DBMs) that significantly accelerates inference (4x to 100x) and improves generation quality by leveraging inverse bridge matching.

We propose a novel algorithm for learning barycentres of distributions using neural networks. The algorithm is scalable and robust to outliers.

We propose a new energy-based method to compute entropic optimal transport barycenters with general cost functions.

We propose a novel theoretically-justified and lightweight solver for continuous unbalanced entropic optimal transport.

We propose a novel bi-level optimization algorithm for solving the continuous Wasserstein Barycenter problem based on Neural Optimal Transport.

We address propose a novel procedure to learn SB which exploits the optimal parameterization of the diffusion process and provably recovers the SB process (a) with a single bridge matching step and (b) with arbitrary transport plan as the input.

We propose a novel algorithm for offline reinforcement learning using optimal transport.

We propose a novel iterative procedure with fast inference to learn the Schrodinger Bridge using the adversarial bridge matching in discrete time.