Unbalanced Diffusion Schr\"odinger Bridge

• URL: http://arxiv.org/abs/2306.09099v1
• Date: Thu, 15 Jun 2023 12:51:56 GMT
• Title: Unbalanced Diffusion Schr\"odinger Bridge
• Authors: Matteo Pariset, Ya-Ping Hsieh, Charlotte Bunne, Andreas Krause, Valentin De Bortoli
• Abstract summary: We introduce unbalanced DSBs which model the temporal evolution of marginals with arbitrary finite mass. This is achieved by deriving the time reversal of differential equations with killing and birth terms. We present two novel algorithmic schemes that comprise a scalable objective function for training unbalanced DSBs.
• Score: 71.31485908125435
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Schr\"odinger bridges (SBs) provide an elegant framework for modeling the temporal evolution of populations in physical, chemical, or biological systems. Such natural processes are commonly subject to changes in population size over time due to the emergence of new species or birth and death events. However, existing neural parameterizations of SBs such as diffusion Schr\"odinger bridges (DSBs) are restricted to settings in which the endpoints of the stochastic process are both probability measures and assume conservation of mass constraints. To address this limitation, we introduce unbalanced DSBs which model the temporal evolution of marginals with arbitrary finite mass. This is achieved by deriving the time reversal of stochastic differential equations with killing and birth terms. We present two novel algorithmic schemes that comprise a scalable objective function for training unbalanced DSBs and provide a theoretical analysis alongside challenging applications on predicting heterogeneous molecular single-cell responses to various cancer drugs and simulating the emergence and spread of new viral variants.

Related papers

• Ergodic repeated interaction quantum systems: Steady states and reducibility theory [0.0]
  We consider the time evolution of an open quantum system subject to a sequence of random quantum channels with a stationary distribution. Various specific models of disorder in repeated interaction models have been considered. We develop a reducarity theory for general stationary random repeated interaction models without this condition.
  arXiv  Detail & Related papers  (2024-06-16T15:38:20Z)
• Determinant and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions [0.0]
  Describing the ground states of continuous, real-space quantum many-body systems is a significant computational challenge. Recent progress was made by variational methods based on machine learning (ML) ansatzes. We argue that combining SRW with path integral techniques leads to a new formulation that overcomes all three problems simultaneously.
  arXiv  Detail & Related papers  (2024-02-09T17:51:32Z)
• Correlational Lagrangian Schr\"odinger Bridge: Learning Dynamics with Population-Level Regularization [27.855576268065857]
  We introduce a novel framework dubbed correlational Lagrangian Schr"odinger bridge ( CLSB) CLSB seeks for the evolution "bridging" among cross-text observations, while regularized for the minimal population "cost" Our contributions include (1) a new class of population regularizers capturing the temporal variations in multivariate relations, with the tractable formulation derived, and (3) three domain-informed instantiations based on genetic co-expression stability.
  arXiv  Detail & Related papers  (2024-02-04T19:33:44Z)
• Eliminating Lipschitz Singularities in Diffusion Models [51.806899946775076]
  We show that diffusion models frequently exhibit the infinite Lipschitz near the zero point of timesteps. This poses a threat to the stability and accuracy of the diffusion process, which relies on integral operations. We propose a novel approach, dubbed E-TSDM, which eliminates the Lipschitz of the diffusion model near zero.
  arXiv  Detail & Related papers  (2023-06-20T03:05:28Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Reconstructing Graph Diffusion History from a Single Snapshot [87.20550495678907]
  We propose a novel barycenter formulation for reconstructing Diffusion history from A single SnapsHot (DASH) We prove that estimation error of diffusion parameters is unavoidable due to NP-hardness of diffusion parameter estimation. We also develop an effective solver named DIffusion hiTting Times with Optimal proposal (DITTO)
  arXiv  Detail & Related papers  (2023-06-01T09:39:32Z)
• Aligned Diffusion Schrödinger Bridges [41.95944857946607]
  Diffusion Schr"odinger bridges (DSBs) have recently emerged as a powerful framework for recovering dynamics via their marginal observations at different time points. Existing algorithms for solving DSBs have so far failed to utilize the structure of aligned data. We propose a novel algorithmic framework that, for the first time, solves DSBs while respecting the data alignment.
  arXiv  Detail & Related papers  (2023-02-22T14:55:57Z)
• Role of boundary conditions in the full counting statistics of topological defects after crossing a continuous phase transition [62.997667081978825]
  We analyze the role of boundary conditions in the statistics of topological defects. We show that for fast and moderate quenches, the cumulants of the kink number distribution present a universal scaling with the quench rate.
  arXiv  Detail & Related papers  (2022-07-08T09:55:05Z)
• Detecting ergodic bubbles at the crossover to many-body localization using neural networks [0.0]
  We propose an algorithm that allows to detect the ergodic bubbles using experimentally measurable two-site correlation functions. Our results open new pathways in studies of the mechanisms of thermalization of disordered many-body systems and beyond.
  arXiv  Detail & Related papers  (2021-06-03T13:03:36Z)
• A General Framework for Survival Analysis and Multi-State Modelling [70.31153478610229]
  We use neural ordinary differential equations as a flexible and general method for estimating multi-state survival models. We show that our model exhibits state-of-the-art performance on popular survival data sets and demonstrate its efficacy in a multi-state setting.
  arXiv  Detail & Related papers  (2020-06-08T19:24:54Z)

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.