English
Related papers

Related papers: Unsupervised operator learning approach for dissip…

200 papers

Real-time dynamics of quantum observables provide direct access to excitation spectra and correlation functions in quantum many-body systems, but currently available quantum devices are limited to short evolution times due to decoherence.…

Quantum Physics · Physics 2026-03-17 Jinyang Li , Satoshi Iso , Shunji Matsuura , Lingxiao Wang , Xiaoyang Wang

In decentralized learning, a network of nodes cooperate to minimize an overall objective function that is usually the finite-sum of their local objectives, and incorporates a non-smooth regularization term for the better generalization…

Machine Learning · Computer Science 2022-01-25 Xuanjie Li , Yuedong Xu , Jessie Hui Wang , Xin Wang , John C. S. Lui

In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, existing offline RL methods are often over-conservative,…

Machine Learning · Computer Science 2023-03-02 Jianxiong Li , Xianyuan Zhan , Haoran Xu , Xiangyu Zhu , Jingjing Liu , Ya-Qin Zhang

Maxwell's equations, a system of linear partial differential equations (PDEs), describe the behavior of electric and magnetic fields in time and space and are essential for many important electromagnetic applications. Although numerical…

Computational Physics · Physics 2026-01-19 Qile Jiang , Marc Salvadori , Dale Ota , Vijaya Shankar , Khemraj Shukla

Recent years have witnessed enormous progress of online learning. However, a major challenge on the road to artificial agents is concept drift, that is, the data probability distribution would change where the data instance arrives…

Machine Learning · Computer Science 2022-01-26 Ya-nan Han , Jian-wei Liu , Bing-biao Xiao , Xin-Tan Wang , Xiong-lin Luo

This contribution proposes novel data-driven surrogate modeling approaches for parameterized parabolic PDEs, where the parameter dependence can be split into two parts with different decay behavior of the Kolmogorov $N$-width. Such problems…

Numerical Analysis · Mathematics 2026-04-27 Dawid Kotowski , Mario Ohlberger

This research gauges the ability of deep reinforcement learning (DRL) techniques to assist the control of conjugate heat transfer systems governed by the coupled Navier--Stokes and heat equations. It uses a novel, "degenerate" version of…

Fluid Dynamics · Physics 2021-03-25 Elie Hachem , Hassan Ghraieb , Jonathan Viquerat , Aurélien Larcher , Philippe Meliga

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement…

Machine Learning · Computer Science 2026-04-09 Chenxu Yang , Chuanyu Qin , Qingyi Si , Minghui Chen , Naibin Gu , Dingyu Yao , Zheng Lin , Weiping Wang , Jiaqi Wang , Nan Duan

Operator learning (OL) has emerged as a powerful tool in scientific machine learning (SciML) for approximating mappings between infinite-dimensional functional spaces. One of its main applications is learning the solution operator of…

Machine Learning · Statistics 2025-08-29 Himanshu Sharma , Lukáš Novák , Michael D. Shields

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

Computation and Language · Computer Science 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

Neural ordinary differential equations (NODEs) -- parametrizations of differential equations using neural networks -- have shown tremendous promise in learning models of unknown continuous-time dynamical systems from data. However, every…

Machine Learning · Computer Science 2023-01-02 Franck Djeumou , Cyrus Neary , Eric Goubault , Sylvie Putot , Ufuk Topcu

We develop a new and general encode-approximate-reconstruct operator learning model that leverages learned neural representations of bases for input and output function distributions. We introduce the concepts of \textit{numerical operator…

Machine Learning · Computer Science 2025-07-11 Jacob Hauck , Yanzhi Zhang

Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a…

Machine Learning · Statistics 2024-08-15 Dong Neuck Lee , Michael R. Kosorok

Deep learning (DL) has driven broad advances across scientific and engineering domains. Despite its success, DL models often exhibit limited interpretability and generalization, which can undermine trust, especially in safety-critical…

Machine Learning · Computer Science 2026-01-14 Atefeh Termehchi , Ekram Hossain , Isaac Woungang

The Koopman operator provides a principled framework for analyzing nonlinear dynamical systems through linear operator theory. Recent advances in dynamic mode decomposition (DMD) have shown that trajectory data can be used to identify…

Machine Learning · Computer Science 2026-01-21 Minchan Jeong , J. Jon Ryu , Se-Young Yun , Gregory W. Wornell

Reinforcement learning (RL) is a powerful paradigm for learning to make sequences of decisions. However, RL has yet to be fully leveraged in robotics, principally due to its lack of scalability. Offline RL offers a promising avenue by…

Machine Learning · Computer Science 2025-10-10 Nicolas Espinosa-Dice , Kiante Brantley , Wen Sun

In this paper, we present a deep neural network based adaptive learning (DNN-AL) approach for switched systems. Currently, deep neural network based methods are actively developed for learning governing equations in unknown dynamic systems,…

Machine Learning · Computer Science 2022-07-12 Junjie He , Zhihang Xu , Qifeng Liao

Reduced-order modeling has a long tradition in computational fluid dynamics. The ever-increasing significance of data for the synthesis of low-order models is well reflected in the recent successes of data-driven approaches such as Dynamic…

Dynamical Systems · Mathematics 2020-12-09 Peter Benner , Pawan Goyal , Jan Heiland , Igor Pontes Duff

Physics-informed neural networks and Physics-informed DeepONet excel in solving partial differential equations; however, they often fail to converge for singularly perturbed problems. To address this, we propose two novel frameworks,…

Machine Learning · Computer Science 2026-04-06 Tiantian Sun , Jian Zu

The aim of this work is to present a model reduction technique in the framework of optimal control problems for partial differential equations. We combine two approaches used for reducing the computational cost of the mathematical numerical…

Numerical Analysis · Mathematics 2023-11-09 Ivan Prusak , Monica Nonino , Davide Torlo , Francesco Ballarin , Gianluigi Rozza