paper-with-me

Papers

SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations

2025-02-04 · Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth

The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation and backpropagation through approximate SDE solutions, which limit scalability. In this work, we propose SDE Matching, a new simulation-free method for training Latent SDEs. Inspired by modern Score- and Flow Matching algorithms for learning generative dynamics, we extend these ideas to the domain of stochastic dynamics for time series and sequence modeling, eliminating the need for costly numerical simulations. Our results demonstrate that SDE Matching achieves performance comparable to adjoint sensitivity methods while drastically reducing computational complexity.

📄 PDF Abstract BibTeX arXiv:2502.02472

Code (0)

등록된 구현이 없습니다.

Tasks

SensitivityTime Series

Similar Papers 제목 키워드 기반

Structured Coupling for Flow Matching

2026-05-08 · Xavier Sumba, Carles Balsells-Rodas, Yingzhen Li arxiv

Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but oft…

Representation Learning

ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation

2026-05-27 · Yu Zhang, Yidi Shao, Wenqi Ouyang, Yushi Lan 외 arxiv

Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graphics, such as 3D visual effects, rendering processes, and motion in vid…

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

2026-06-21 · Serge Thilges, Onur Celik, Denis Blessing, Emiliyan Gospodinov 외 arxiv

Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of sc…

Reinforcement Learning

HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition

2026-04-21 · Xiaoqi Zhuang, Jefersson A. Dos Santos, Jungong Han arxiv

Satellite image composition plays a critical role in remote sensing applications such as data augmentation, disaste simulation, and urban planning. We propose HarmoniDiff-RS, a training-free diffusion-based framework for…

Image HarmonizationData Augmentation

Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation

2026-05-06 · Zimu Gong, Brian Zhaoning Zhang, Chris Zhang, Kelvin Wong 외 arxiv

Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation offers a way to generate such scenarios, manually designed test cases lac…

Autonomous Vehicles