中文
相关论文

相关论文: Lagrangian Flow Matching: A Least-Action Framework…

200 篇论文

Backpropagation is typically presented as a symbolic procedure: a backward pass topologically distinct from inference, with non-local error signals and synchronous global clocking, features with no clear analog in physical reality. Existing…

机器学习 · 计算机科学 2026-05-12 Antonino Emanuele Scurria

We investigate the optimal transport problem between probability measures when the underlying cost function is understood to satisfy a least action principle, also known as a Lagrangian cost. These generalizations are useful when connecting…

机器学习 · 计算机科学 2024-06-04 Aram-Alexandre Pooladian , Carles Domingo-Enrich , Ricky T. Q. Chen , Brandon Amos

The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (potential energy). These combinations yield different…

机器学习 · 计算机科学 2024-07-04 Kirill Neklyudov , Rob Brekelmans , Alexander Tong , Lazar Atanackovic , Qiang Liu , Alireza Makhzani

The log-homotopy particle flow filter resolves the Bayesian update by transporting particles along a continuous trajectory in pseudo-time. However, the governing partial differential equation for the flow velocity is fundamentally…

系统与控制 · 电气工程与系统科学 2026-05-18 Olivér Törő , Domonkos Csuzdi , Tamás Bécsi

Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which…

机器学习 · 统计学 2024-11-11 Nikita Kornilov , Petr Mokrov , Alexander Gasnikov , Alexander Korotin

This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields that guide transformations from a source…

机器学习 · 计算机科学 2026-02-17 Johannes Hertrich , Antonin Chambolle , Julie Delon

Training learning parameterizations to solve optimal power flow (OPF) with pointwise constraints is proposed. In this novel training approach, a learning parameterization is substituted directly into an OPF problem with constraints required…

系统与控制 · 电气工程与系统科学 2025-10-24 Damian Owerko , Anna Scaglione , Alejandro Ribeiro

Predicting particle transport in complex flows is traditionally achieved by solving the Navier-Stokes equations. While various numerical and experimental methods exist, they typically require deep physical insights and incur high…

流体动力学 · 物理学 2025-11-03 Jingdi Wan , Hongping Wang , Bo Liu , Xiaolei Yang , Xiaodong Hu , Shengze Cai , Guowei He , Yang Liu

We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon…

机器学习 · 计算机科学 2025-09-26 Siyuan Guo , Bernhard Schölkopf

Flow Matching (FM) is an effective framework for training a model to learn a vector field that transports samples from a source distribution to a target distribution. To train the model, early FM methods use random couplings, which often…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Yexiong Lin , Yu Yao , Tongliang Liu

We propose an algorithm using method of evolving junctions to solve the optimal path planning problems with piece-wise constant flow fields. In such flow fields with a convex Lagrangian in the objective function, we can prove that the…

最优化与控制 · 数学 2021-12-14 Haoyan Zhai , Mengxue Hou , Fumin Zhang , Haomin Zhou

Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlying dynamical systems. However, it is not well-understood whether it learns transferable dynamical…

机器学习 · 统计学 2026-05-08 Soon Hoe Lim , Shizheng Lin , Michael W. Mahoney , N. Benjamin Erichson

Foundations of a new projection-based model reduction approach for convection dominated nonlinear fluid flows are summarized. In this method the evolution of the flow is approximated in the Lagrangian frame of reference. Global basis…

流体动力学 · 物理学 2021-10-05 Rambod Mojgani , Maciej Balajewicz

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It…

信号处理 · 电气工程与系统科学 2019-12-04 Ferdinando Fioretto , Terrence W. K. Mak , Pascal Van Hentenryck

Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about the underlying process in order to enable faithful learning…

We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. By construction, the proposed LFlows satisfy the continuity equation, a PDE describing mass conservation in its…

机器学习 · 计算机科学 2023-12-15 F. Arend Torres , Marcello Massimo Negri , Marco Inversi , Jonathan Aellen , Volker Roth

Learning probabilistic surrogates for partial differential equations remains challenging in data-scarce regimes: neural operators require large amounts of high-fidelity data, while generative approaches typically sacrifice resolution…

统计计算 · 统计学 2025-12-18 Sahil Bhola , Karthik Duraisamy

Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions $p_t$. We identify a geometric optimization bottleneck in this regression problem: when the covariance $\Sigma_t$ of $p_t$ is…

机器学习 · 计算机科学 2026-05-14 Shadab Ahamed , Eshed Gal , Md Shahriar Rahim Siddiqui , Simon Ghyselincks , Moshe Eliasof , Eldad Haber

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating…

机器人学 · 计算机科学 2025-03-11 Khang Nguyen , An T. Le , Tien Pham , Manfred Huber , Jan Peters , Minh Nhat Vu

The principle of least action is one of the most fundamental physical principle. It says that among all possible motions connecting two points in a phase space, the system will exhibit those motions which extremise an action functional.…

数值分析 · 数学 2022-10-17 Sina Ober-Blöbaum , Christian Offen
‹ 上一页 1 2 3 10 下一页 ›