Soft-constrained Schrodinger Bridge: a Stochastic Control Approach
Schr\"{o}dinger bridge can be viewed as a continuous-time stochastic control problem where the goal is to find an optimally controlled diffusion process whose terminal distribution coincides with a pre-specified target distribution. We propose to generalize this problem by allowing the terminal distribution to differ from the target but penalizing the Kullback-Leibler divergence between the two distributions. We call this new control problem soft-constrained Schr\"{o}dinger bridge (SSB). The main contribution of this work is a theoretical derivation of the solution to SSB, which shows that the terminal distribution of the optimally controlled process is a geometric mixture of the target and some other distribution. This result is further extended to a time series setting. One application is the development of robust generative diffusion models. We propose a score matching-based algorithm for sampling from geometric mixtures and showcase its use via a numerical example for the MNIST data set.
Code (0)
등록된 구현이 없습니다.
Tasks
Time SeriesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Entropy-Controlled Flow Matching
Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow…
Steering Large Agent Populations using Mean-Field Schrodinger Bridges with Gaussian Mixture Models
The Mean-Field Schrodinger Bridge (MFSB) problem is an optimization problem aiming to find the minimum effort control policy to drive a McKean-Vlassov stochastic differential equation from one probability measure to anot…
Stochastic OptimizationXFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges
Generative robotic motion planning requires not only the synthesis of smooth and collision-free trajectories but also feasibility across diverse tasks and dynamic constraints. Prior planning methods, both traditional and…
Motion PlanningLatent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However, they often require a larger number of n…
Image GenerationImage-to-Image TranslationTranslationSchrödinger bridge for generative AI: Soft-constrained formulation and convergence analysis
Generative AI can be framed as the problem of learning a model that maps simple reference measures into complex data distributions, and it has recently found a strong connection to the classical theory of the Schrödinger…
Transfer Learning