English
Related papers

Related papers: Applying Regularized Schr\"odinger-Bridge-Based St…

200 papers

In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such…

Machine Learning · Computer Science 2021-06-14 Yucheng Lu , Youngsuk Park , Lifan Chen , Yuyang Wang , Christopher De Sa , Dean Foster

Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling…

Machine Learning · Computer Science 2021-06-28 Zexuan Yin , Paolo Barucca

Recent innovations in diffusion probabilistic models have paved the way for significant progress in image, text and audio generation, leading to their applications in generative time series forecasting. However, leveraging such abilities to…

Machine Learning · Computer Science 2025-11-07 Yuansan Liu , Sudanthi Wijewickrema , Dongting Hu , Christofer Bester , Stephen O'Leary , James Bailey

Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schr\"odinger Bridges. Our proposal generalizes prior work by allowing the reference process in the Schr\"odinger Bridge problem to be a smooth…

Machine Learning · Statistics 2025-03-04 Wanli Hong , Yuliang Shi , Jonathan Niles-Weed

Stochastic flows of an advective-diffusive nature are ubiquitous in physical sciences. Of particular interest is the problem to reconcile observed marginal distributions with a given prior posed by E. Schrodinger in 1932/32 and known as the…

Mathematical Physics · Physics 2021-08-09 Yongxin Chen , Tryphon T. Georgiou , Michele Pavon

Sequential recommendation has attracted increasing attention due to its ability to accurately capture the dynamic changes in user interests. We have noticed that generative models, especially diffusion models, which have achieved…

Information Retrieval · Computer Science 2024-09-18 Wenjia Xie , Rui Zhou , Hao Wang , Tingjia Shen , Enhong Chen

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

Machine Learning · Computer Science 2025-10-27 Myunsoo Kim , Donghyeon Ki , Seong-Woong Shim , Byung-Jun Lee

In this paper, we investigate the multi-marginal Schrodinger bridge (MSB) problem whose marginal constraints are marginal distributions of a stochastic differential equation (SDE) with a constant diffusion coefficient, and with time…

Probability · Mathematics 2025-07-15 Rentian Yao , Young--Heon Kim , Geoffrey Schiebinger

Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dimensional data…

Machine Learning · Computer Science 2025-12-12 Defang Chen , Zhenyu Zhou , Can Wang , Siwei Lyu

The numerical quantification of the statistics of rare events in stochastic processes is a challenging computational problem. We present a sampling method that constructs an ensemble of stochastic trajectories that are constrained to have…

Statistical Mechanics · Physics 2022-07-13 Javier Aguilar , Joseph W. Baron , Tobias Galla , Raul Toral

A plethora of recent research has focused on improving the memory footprint and inference speed of deep networks by reducing the complexity of (i) numerical representations (for example, by deterministic or stochastic quantization) and (ii)…

Machine Learning · Computer Science 2019-04-05 David Hartmann , Michael Wand

The solution of the path structured multimarginal Schr\"{o}dinger bridge problem (MSBP) is the most-likely measure-valued trajectory consistent with a sequence of observed probability measures or distributional snapshots. We leverage recent…

Systems and Control · Electrical Eng. & Systems 2023-10-05 Georgiy A. Bondar , Robert Gifford , Linh Thi Xuan Phan , Abhishek Halder

Modern real-time systems require accurate characterization of task timing behavior to ensure predictable performance, particularly on complex hardware architectures. Existing methods, such as worst-case execution time analysis, often fail…

Systems and Control · Electrical Eng. & Systems 2026-04-03 Georgiy A. Bondar , Abigail Eisenklam , Yifan Cai , Robert Gifford , Tushar Sial , Linh Thi Xuan Phan , Abhishek Halder

Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schr\"odinger…

High Energy Physics - Phenomenology · Physics 2025-06-25 Anja Butter , Sascha Diefenbacher , Nathan Huetsch , Vinicius Mikuni , Benjamin Nachman , Sofia Palacios Schweitzer , Tilman Plehn

In this work, we revisit the discrete-time Schr\"{o}dinger Bridge (SB) and Density Steering (DS) problems for Gaussian mixture model (GMM) boundary distributions. Building on the existing literature, we construct a set of feasible Markovian…

Systems and Control · Electrical Eng. & Systems 2026-04-02 George Rapakoulias , Fengjiao Liu , Panagiotis Tsiotras

Modeling the dynamics from sparsely time-resolved snapshot data is crucial for understanding complex cellular processes and behavior. Existing methods leverage optimal transport, Schr\"odinger bridge theory, or their variants to…

Machine Learning · Computer Science 2025-10-28 Zhenyi Zhang , Zihan Wang , Yuhao Sun , Tiejun Li , Peijie Zhou

In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form…

Machine Learning · Computer Science 2025-02-28 Saeid Naderiparizi , Xiaoxuan Liang , Berend Zwartsenberg , Frank Wood

Reconstructing dynamics using samples from sparsely time-resolved snapshots is an important problem in both natural sciences and machine learning. Here, we introduce a new deep learning approach for solving regularized unbalanced optimal…

Machine Learning · Computer Science 2025-05-09 Zhenyi Zhang , Tiejun Li , Peijie Zhou

Understanding complex systems by inferring trajectories from sparse sample snapshots is a fundamental challenge in a wide range of domains, e.g., single-cell biology, meteorology, and economics. Despite advancements in Bridge and Flow…

The breeding method is a computationally cheap way to generate flow-adapted ensembles to be used in probabilistic forecasts. Its main disadvantage is that the ensemble may lack diversity and collapse to a low-dimensional subspace. To still…

Atmospheric and Oceanic Physics · Physics 2019-05-01 Brent Giggins , Georg A. Gottwald