English
Related papers

Related papers: Symplectic Generative Networks (SGNs): A Hamiltoni…

200 papers

Following early work on Hessian-free methods for deep learning, we study a stochastic generalized Gauss-Newton method (SGN) for training DNNs. SGN is a second-order optimization method, with efficient iterations, that we demonstrate to…

Machine Learning · Computer Science 2020-06-11 Matilde Gargiani , Andrea Zanelli , Moritz Diehl , Frank Hutter

Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and broadly adopted as an effective approach to improve the performance of smaller but more resource and compute efficient LLMs through…

Machine Learning · Computer Science 2026-03-25 Srideepika Jayaraman , Achille Fokoue , Dhaval Patel , Jayant Kalagnanam

HNets is a class of neural networks on grounds of physical prior for learning Hamiltonian systems. This paper explains the influences of different integrators as hyper-parameters on the HNets through error analysis. If we define the network…

Numerical Analysis · Mathematics 2020-04-30 Aiqing Zhu , Pengzhan Jin , Yifa Tang

Sum-Product Networks (SPNs) are hierarchical, graphical models that combine benefits of deep learning and probabilistic modeling. SPNs offer unique advantages to applications demanding exact probabilistic inference over high-dimensional,…

Machine Learning · Computer Science 2020-09-24 Jos van de Wolfshaar , Andrzej Pronobis

Canonical transformation plays a fundamental role in simplifying and solving classical Hamiltonian systems. We construct flexible and powerful canonical transformations as generative models using symplectic neural networks. The model…

Statistical Mechanics · Physics 2020-04-29 Shuo-Hui Li , Chen-Xiao Dong , Linfeng Zhang , Lei Wang

Deep generative models (DGM) are neural networks with many hidden layers trained to approximate complicated, high-dimensional probability distributions using a large number of samples. When trained successfully, we can use the DGMs to…

Machine Learning · Computer Science 2021-04-13 Lars Ruthotto , Eldad Haber

Simulation-Grounded Neural Networks (SGNNs) are predictive models trained entirely on synthetic data from mechanistic simulations. They have achieved state-of-the-art performance in domains where real-world labels are limited or unobserved,…

Machine Learning · Computer Science 2025-10-03 Carson Dudley , Marisa Eisenberg

We propose an effective and lightweight learning algorithm, Symplectic Taylor Neural Networks (Taylor-nets), to conduct continuous, long-term predictions of a complex Hamiltonian dynamic system based on sparse, short-term observations. At…

Machine Learning · Computer Science 2022-02-22 Yunjin Tong , Shiying Xiong , Xingzhe He , Guanghan Pan , Bo Zhu

We propose a new symplectic convolutional neural network (CNN) architecture by leveraging symplectic neural networks, proper symplectic decomposition, and tensor techniques. Specifically, we first introduce a mathematically equivalent form…

Machine Learning · Computer Science 2026-02-06 Süleyman Yıldız , Konrad Janik , Peter Benner

Data-centric methods have shown great potential in understanding and predicting spatiotemporal dynamics, enabling better design and control of the object system. However, deep learning models often lack interpretability, fail to obey…

Machine Learning · Computer Science 2025-01-07 Yuan Mi , Pu Ren , Hongteng Xu , Hongsheng Liu , Zidong Wang , Yike Guo , Ji-Rong Wen , Hao Sun , Yang Liu

From metronomes to celestial bodies, mechanics underpins how the world evolves in time and space. With consideration of this, a number of recent neural network models leverage inductive biases from classical mechanics to encourage model…

Machine Learning · Computer Science 2026-01-15 Jiayin Liu , Yulong Yang , Vineet Bansal , Christine Allen-Blanchette

R\'enyi's information provides a theoretical foundation for tractable and data-efficient non-parametric density estimation, based on pair-wise evaluations in a reproducing kernel Hilbert space (RKHS). This paper extends this framework to…

Machine Learning · Computer Science 2022-03-09 Bo Hu , Shujian Yu , Jose C. Principe

Generative methods have recently seen significant improvements by generating in a lower-dimensional latent representation of the data. However, many of the generative methods applied in the latent space remain complex and difficult to…

Machine Learning · Computer Science 2025-01-22 Alona Levy-Jurgenson , Zohar Yakhini

Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions…

Machine Learning · Computer Science 2017-09-26 Boris Flach , Alexander Shekhovtsov , Ondrej Fikar

In this work, we present and study Continuous Generative Neural Networks (CGNNs), namely, generative models in the continuous setting: the output of a CGNN belongs to an infinite-dimensional function space. The architecture is inspired by…

Machine Learning · Statistics 2025-06-25 Giovanni S. Alberti , Matteo Santacesaria , Silvia Sciutto

Deep learning is widely used in tasks including image recognition and generation, in learning dynamical systems from data and many more. It is important to construct learning architectures with theoretical guarantees to permit safety in the…

Numerical Analysis · Mathematics 2024-06-07 Sofya Maslovskaya , Sina Ober-Blöbaum

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent)…

Machine Learning · Computer Science 2025-04-22 Dimitris G. Giovanis , Ellis Crabtree , Roger G. Ghanem , Ioannis G. Kevrekidis

The modeling and simulation of infinite-dimensional Hamiltonian systems are central problems in mathematical physics and engineering, however they pose significant computational and structural challenges for standard data-driven…

Dynamical Systems · Mathematics 2026-05-18 Yeang Makara , Yusuke Tanaka , Takashi Matsubara , Takaharu Yaguchi

We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) to their templates. Our proposed framework is fully…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Elvis Nunez , Andrew Lizarraga , Shantanu H. Joshi

Generative adversarial networks (GANs) have attracted intense interest in the field of generative models. However, few investigations focusing either on the theoretical analysis or on algorithm design for the approximation ability of the…

Machine Learning · Computer Science 2020-07-14 Xuejiao Liu , Yao Xu , Xueshuang Xiang