SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models
Generative Latent Kernel Modeling for Blind Motion Deblurring
Towards Interpretable Time Series Foundation Models
MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection
skfolio: Portfolio Optimization in Python
토론
이 논문과 연결된 포럼 글이 아직 없습니다.