paper-with-me

Papers

Soft-constrained Schrodinger Bridge: a Stochastic Control Approach

2024-03-04 · Jhanvi Garg, Xianyang Zhang, Quan Zhou

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.

📄 PDF Abstract BibTeX arXiv:2403.01717

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Entropy-Controlled Flow Matching

2026-02-25 · Chika Maduabuchi arxiv

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

2025-03-31 · George Rapakoulias, Ali Reza Pedram, Panagiotis Tsiotras

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 Optimization

XFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges

2025-11-02 · Khang Nguyen, Minh Nhat Vu arxiv

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 Planning

Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation

2024-11-22 · Jeongsol Kim, Beomsu Kim, Jong Chul Ye

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 TranslationTranslation

Schrödinger bridge for generative AI: Soft-constrained formulation and convergence analysis

2025-10-13 · Jin Ma, Ying Tan, Renyuan Xu arxiv

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