Multi-Marginal Schrödinger Bridge Matching

• URL: http://arxiv.org/abs/2510.16587v1
• Date: Sat, 18 Oct 2025 17:21:19 GMT
• Title: Multi-Marginal Schrödinger Bridge Matching
• Authors: Byoungwoo Park, Juho Lee,
• Abstract summary: This paper introduces Multi-Marginal Schr"odinger Bridge Matching (MSBM), a novel algorithm specifically designed for the multi-marginal SB problem.<n>MSBM extends iterative Markovian fitting (IMF) to effectively handle multiple marginal constraints.<n> Empirical validations on synthetic data and real-world single-cell RNA sequencing datasets demonstrate the competitive or superior performance of MSBM.
• Score: 17.207066323031494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding the continuous evolution of populations from discrete temporal snapshots is a critical research challenge, particularly in fields like developmental biology and systems medicine where longitudinal tracking of individual entities is often impossible. Such trajectory inference is vital for unraveling the mechanisms of dynamic processes. While Schr\"odinger Bridge (SB) offer a potent framework, their traditional application to pairwise time points can be insufficient for systems defined by multiple intermediate snapshots. This paper introduces Multi-Marginal Schr\"odinger Bridge Matching (MSBM), a novel algorithm specifically designed for the multi-marginal SB problem. MSBM extends iterative Markovian fitting (IMF) to effectively handle multiple marginal constraints. This technique ensures robust enforcement of all intermediate marginals while preserving the continuity of the learned global dynamics across the entire trajectory. Empirical validations on synthetic data and real-world single-cell RNA sequencing datasets demonstrate the competitive or superior performance of MSBM in capturing complex trajectories and respecting intermediate distributions, all with notable computational efficiency.

Related papers

• Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process [55.91649771370862]
  Dirichlet process (DP) mixture model is a powerful non-parametric method that can amplify the most prominent features.<n>We propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-10-23T16:53:24Z)
• Multi-marginal temporal Schrödinger Bridge Matching for video generation from unpaired data [1.004996690798013]
  We propose textittextbfMulti-Marginal temporal Schr"odinger Bridge Matching (textbfMMtSBM)<n>Our work establishes MMtSBM as a practical and principled approach for recovering hidden dynamics from static data.<n> Experiments show that MMtSBM retains theoretical properties on toy examples, achieves state-of-the-art performance on real world datasets, and for the first time recovers couplings and dynamics in very high dimensional image settings.
  arXiv  Detail & Related papers  (2025-10-02T11:00:58Z)
• Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning [56.240199425429445]
  Multi-Robot Motion Planning (MPMP) involves generating trajectories for multiple robots operating in a shared continuous workspace.<n>While discrete multi-agent finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization trajectory quality.<n>This paper tackles limitations of two approaches by introducing discrete MAPF solvers with constrained generative diffusion models.
  arXiv  Detail & Related papers  (2025-08-27T17:59:36Z)
• FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming [52.52020895303244]
  Mixed-Integer Linear Programming (MILP) is a foundational tool for complex decision-making problems.<n>We propose Joint Continuous-Integer Flow for Mixed-Integer Linear Programming (FMIP), which is the first generative framework that models joint distribution of both integer and continuous variables for MILP solutions.<n>FMIP is fully compatible with arbitrary backbone networks and various downstream solvers, making it well-suited for a broad range of real-world MILP applications.
  arXiv  Detail & Related papers  (2025-07-31T10:03:30Z)
• Momentum Multi-Marginal Schrödinger Bridge Matching [20.53138254276056]
  We introduce textbfMomentum Multi-Marginal Schr"odinger Bridge Matching (3MSBM), a novel matching framework that learns smooth measure-valued splines for systems that satisfy multiple positional constraints.<n>As a matching approach, 3MSBM learns transport maps that preserve intermediate marginals throughout training, significantly improving convergence and scalability.
  arXiv  Detail & Related papers  (2025-06-11T20:41:23Z)
• Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences [60.489682735061415]
  We propose CHELA, which replaces state space models with short-long convolutions and implements linear attention in a divide-and-conquer manner. Our experiments on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-06-12T12:12:38Z)
• Adversarial Schrödinger Bridge Matching [66.39774923893103]
  Iterative Markovian Fitting (IMF) procedure alternates between Markovian and reciprocal projections of continuous-time processes. We propose a novel Discrete-time IMF (D-IMF) procedure in which learning of processes is replaced by learning just a few transition probabilities in discrete time. We show that our D-IMF procedure can provide the same quality of unpaired domain translation as the IMF, using only several generation steps instead of hundreds.
  arXiv  Detail & Related papers  (2024-05-23T11:29:33Z)
• Markovletics: Methods and A Novel Application for Learning Continuous-Time Markov Chain Mixtures [11.131861804842886]
  We study learning mixtures of continuous-time Markov chains (CTMCs) CTMCs could model intricate continuous-time processes prevalent in various fields including social media, finance, and biology. We introduce a novel framework for exploring CTMCs, emphasizing the influence of observed trails' length and mixture parameters on problem regimes. We apply our algorithms on an extensive collection of Lastfm's user-generated trails spanning three years, demonstrating the capability of our algorithms to differentiate diverse user preferences.
  arXiv  Detail & Related papers  (2024-02-27T18:04:59Z)
• Generalized Schrödinger Bridge Matching [54.171931505066]
  Generalized Schr"odinger Bridge (GSB) problem setup is prevalent in many scientific areas both within and without machine learning. We propose Generalized Schr"odinger Bridge Matching (GSBM), a new matching algorithm inspired by recent advances. We show that such a generalization can be cast as solving conditional optimal control, for which variational approximations can be used.
  arXiv  Detail & Related papers  (2023-10-03T17:42:11Z)
• Monotone deep Boltzmann machines [86.50247625239406]
  Deep Boltzmann machines (DBMs) are multi-layered probabilistic models governed by a pairwise energy function. We develop a new class of restricted model, the monotone DBM, which allows for arbitrary self-connection in each layer. We show that a particular choice of activation results in a fixed-point iteration that gives a variational mean-field solution.
  arXiv  Detail & Related papers  (2023-07-11T03:02:44Z)
• Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation [28.83712379658548]
  We develop FedMSA, the first federated approximation algorithm for multiple coupled sequences (MSA) FedMSA enables the provable estimation of hypergradients in BLO and MCO via local client updates. We provide experiments that support our theory and demonstrate the empirical benefits of FedMSA.
  arXiv  Detail & Related papers  (2023-06-02T16:17:43Z)
• Deep Momentum Multi-Marginal Schr\"odinger Bridge [41.27274841596343]
  We present a novel framework that learns the smooth measure-valued algorithm for systems that satisfy position marginal constraints across time. Our algorithm outperforms baselines significantly, as evidenced by experiments for synthetic datasets and a real-world single-cell RNA dataset sequence.
  arXiv  Detail & Related papers  (2023-03-03T07:24:38Z)
• Formal Controller Synthesis for Markov Jump Linear Systems with Uncertain Dynamics [64.72260320446158]
  We propose a method for synthesising controllers for Markov jump linear systems. Our method is based on a finite-state abstraction that captures both the discrete (mode-jumping) and continuous (stochastic linear) behaviour of the MJLS. We apply our method to multiple realistic benchmark problems, in particular, a temperature control and an aerial vehicle delivery problem.
  arXiv  Detail & Related papers  (2022-12-01T17:36:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.