Modeling non-Euclidean data is drawing extensive attention along with the unprecedented successes of deep neural networks in diverse fields. Particularly, a symmetric positive definite matrix is being actively studied in computer vision, signal processing, and medical image analysis, due to its ability to learn beneficial statistical representations. However, owing to its rigid constraints, it remains challenging to optimization problems and inefficient computational costs, especially, when incorporating it with a deep learning framework. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifolds and a Cholesky space, by which it becomes feasible not only to efficiently solve optimization problems but also to greatly reduce computation costs. Further, for dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network. It is worth noting that due to the nice parameterization of matrices in a Cholesky space, training our proposed network equipped with Riemannian geometric metrics is straightforward. We demonstrate through experiments over regular and irregular time-series datasets that our proposed model can be efficiently and reliably trained and outperforms existing manifold methods and state-of-the-art methods in various time-series tasks.
Hierarchical Stochastic Differential Equation Models for Latent Manifold Learning in Neural Time Series
Department of Biomedical Engineering(生物医学工程系);University of Houston(休斯顿大学);Department of Electrical and Computer Engineering(电气与计算机工程系);Isfahan University of Technology(伊斯法罕技术大学)
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
McGill University(麦吉尔大学);Mila - Quebec AI Institute(魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);University of Toronto(多伦多大学);Concordia University(康科迪亚大学);com(42.com)
Università degli Studi di Napoli Federico II(那不勒斯费德里科二世大学);Technion — Israel Institute of Technology(以色列理工学院);Johns Hopkins University(约翰斯·霍普金斯大学);Scuola Superiore Meridionale(南方高等学校)
A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks
Yingcai Honors College, University of Electronic Science and Technology of China(电子科技大学荣誉学院);School of Mathematical Sciences, University of Electronic Science and Technology of China(电子科技大学数学学院);College of Computer Sciences, Sichuan University(四川大学计算机学院)
STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting
School of Artificial Intelligence and Robotics, Xiamen University Malaysia(厦门大学马来西亚分校人工智能与机器人学院);S.M.A.R.T. NEXUS Centre of Excellence, Xiamen University Malaysia(厦门大学马来西亚分校S.M.A.R.T. NEXUS卓越研究中心)
Emergent Riemannian geometry over learning discrete computations on continuous manifolds
School of Informatics University of Edinburgh(信息学院爱丁堡大学);Département d’Etudes Cognitives Ecole Normale Supérieure PSL(认知研究部巴黎高等师范学院PSL);Gastsby Unit University College London(加斯特比单位伦敦大学学院);Data Science Center Ecole Normale Supérieure PSL(数据科学中心巴黎高等师范学院PSL)
FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
Medical & Imaging Informatics (MII) Group, University of California, Los Angeles (UCLA), CA, USA(加州大学洛杉矶分校医学与影像信息学组);Department of Industrial Engineering, Ulsan National Institute of Science and Technology (UNIST), Republic of Korea(韩国蔚山科学技术院工业工程系);Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST), Republic of Korea(韩国蔚山科学技术院人工智能研究生院)