English
Related papers

Related papers: STEER: Simple Temporal Regularization For Neural O…

200 papers

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

We investigate neural ordinary and stochastic differential equations (neural ODEs and SDEs) to model stochastic dynamics in fully and partially observed environments within a model-based reinforcement learning (RL) framework. Through a…

Machine Learning · Computer Science 2026-03-25 Chao Han , Stefanos Ioannou , Luca Manneschi , T. J. Hayward , Michael Mangan , Aditya Gilra , Eleni Vasilaki

Neural networks have shown great potential in accelerating the solution of partial differential equations (PDEs). Recently, there has been a growing interest in introducing physics constraints into training neural PDE solvers to reduce the…

Machine Learning · Computer Science 2023-05-30 Xinquan Huang , Wenlei Shi , Qi Meng , Yue Wang , Xiaotian Gao , Jia Zhang , Tie-Yan Liu

Adversarial training is a common approach to improving the robustness of deep neural networks against adversarial examples. In this work, we propose a novel regularization approach as an alternative. To derive the regularizer, we formulate…

Machine Learning · Computer Science 2021-02-09 Avery Ma , Fartash Faghri , Nicolas Papernot , Amir-massoud Farahmand

Model regularization requires extensive manual tuning to balance complexity against overfitting. Cross-regularization resolves this tradeoff by directly adapting regularization parameters through validation gradients during training. The…

Machine Learning · Computer Science 2025-06-25 Carlos Stein Brito

Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Yunfan Ye , Renjiao Yi , Zhiping Cai , Kai Xu

In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first interpret momentum as solving an $\ell_2$-regularized…

Machine Learning · Computer Science 2019-06-04 Ziming Zhang , Wenju Xu , Alan Sullivan

Stiff ordinary differential equations (ODEs) are common in many science and engineering fields, but standard neural ODE approaches struggle to accurately learn these stiff systems, posing a significant barrier to widespread adoption of…

Numerical Analysis · Mathematics 2024-12-03 Colby Fronk , Linda Petzold

In this paper we consider new regularization methods for linear inverse problems of dynamic type. These methods are based on dynamic programming techniques for linear quadratic optimal control problems. Two different approaches are…

Numerical Analysis · Mathematics 2021-01-26 S. Kindermann , A. Leitao

Using vanilla NeuralODEs to model large and/or complex systems often fails due two reasons: Stability and convergence. NeuralODEs are capable of describing stable as well as instable dynamic systems. Selecting an appropriate numerical…

Machine Learning · Computer Science 2023-02-23 Tobias Thummerer , Lars Mikelsons

We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In…

Neural and Evolutionary Computing · Computer Science 2015-02-20 Wojciech Zaremba , Ilya Sutskever , Oriol Vinyals

Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present…

Machine Learning · Computer Science 2024-12-17 Hong Zhang , Ying Liu , Romit Maulik

PDE-constrained optimal control problems require regularisation to ensure well-posedness, introducing small perturbations that make the solutions challenging to approximate accurately. We propose a finite element approach that couples both…

Numerical Analysis · Mathematics 2025-03-17 Jenny Power , Tristan Pryer

To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN architectures using numerical methods of ordinary differential…

Machine Learning · Computer Science 2019-05-01 Murphy Yuezhen Niu , Lior Horesh , Isaac Chuang

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation…

We consider the ill-posed inverse problem of identifying a nonlinearity in a time-dependent PDE model. The nonlinearity is approximated by a neural network, and needs to be determined alongside other unknown physical parameters and the…

Numerical Analysis · Mathematics 2022-11-23 Barbara Kaltenbacher , Tram Thi Ngoc Nguyen

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan

We investigate continuous regularization methods for linear inverse problems of static and dynamic type. These methods are based on dynamic programming approaches for linear quadratic optimal control problems. We prove regularization…

Optimization and Control · Mathematics 2021-01-27 S. Kindermann , A. Leitao

In this thesis, we draw inspiration from both classical system identification and modern machine learning in order to solve estimation problems for real-world, physical systems. The main approach to estimation and learning adopted is…

Machine Learning · Computer Science 2024-09-23 Fredrik Bagge Carlson

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Machine Learning · Computer Science 2024-08-21 Huixiu Jiang , Ling Yang , Yu Bao , Rutong Si , Sikun Yang