English
Related papers

Related papers: Adaptive-saturated RNN: Remember more with less in…

200 papers

This paper establishes an approximation theorem for randomized neural networks (RaNNs) whose hidden-layer parameters are uniformly sampled from a prescribed bounded domain. Our analysis shows that, for RaNNs of the form $\mathop{\sum}_i W_i…

Numerical Analysis · Mathematics 2026-04-13 Ran Bi , Weibing Deng

Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage…

Machine Learning · Computer Science 2024-06-17 Shuai Wang , David W. Zhang , Jia-Hong Huang , Stevan Rudinac , Monika Kackovic , Nachoem Wijnberg , Marcel Worring

We consider applications of neural networks in nonlinear system identification and formulate a hypothesis that adjusting general network structure by incorporating frequency information or other known orthogonal transform, should result in…

Machine Learning · Computer Science 2025-01-24 Krzysztof Zając , Wojciech Sopot , Paweł Wachel

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…

Machine Learning · Computer Science 2020-09-01 Angelos Katharopoulos , Apoorv Vyas , Nikolaos Pappas , François Fleuret

We propose a method for efficiently incorporating constraints into a stochastic gradient Langevin framework for the training of deep neural networks. Constraints allow direct control of the parameter space of the model. Appropriately…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Timothée Pouchon , Tiffany Vlaar , Amos Storkey

Active learning optimizes the exploration of large parameter spaces by strategically selecting which experiments or simulations to conduct, thus reducing resource consumption and potentially accelerating scientific discovery. A key…

Machine Learning · Computer Science 2024-05-20 Maxim Ziatdinov

With the introduction of the transformer architecture in computer vision, increasing model scale has been demonstrated as a clear path to achieving performance and robustness gains. However, with model parameter counts reaching the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Jochem Loedeman , Maarten C. Stol , Tengda Han , Yuki M. Asano

Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters…

Machine Learning · Computer Science 2026-05-22 Kun-Peng Ning , Hai-Jian Ke , Yu-Yang Liu , Jia-Yu Yao , Yong-Hong Tian , Li Yuan

Accurately modeling quantum dissipative dynamics remains challenging due to environmental complexity and non-Markovian memory effects. Although machine learning provides a promising alternative to conventional simulation techniques, most…

Chemical Physics · Physics 2026-03-18 Muhammad Atif , Arif Ullah , Ming Yang

Graph Neural Networks have recently become a prevailing paradigm for various high-impact graph analytical problems. Existing efforts can be mainly categorized as spectral-based and spatial-based methods. The major challenge for the former…

Machine Learning · Computer Science 2022-02-22 Yushun Dong , Kaize Ding , Brian Jalaian , Shuiwang Ji , Jundong Li

Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…

Machine Learning · Computer Science 2019-12-17 Mihai Suteu , Yike Guo

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and…

Machine Learning · Computer Science 2024-07-18 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Wensheng Zhang , Zhi Han , Yuan Xie

Adaptive nuclear-norm penalization is proposed for low-rank matrix approximation, by which we develop a new reduced-rank estimation method for the general high-dimensional multivariate regression problems. The adaptive nuclear norm of a…

Methodology · Statistics 2012-09-25 Kun Chen , Hongbo Dong , Kung-Sik Chan

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us to rethink generalization by bringing forth new phenomena,…

Machine Learning · Statistics 2020-12-01 Vatsal Shah , Soumya Basu , Anastasios Kyrillidis , Sujay Sanghavi

Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point…

Neural and Evolutionary Computing · Computer Science 2025-12-02 Xingting Yao , Qinghao Hu , Fei Zhou , Tielong Liu , Gang Li , Peisong Wang , Jian Cheng

This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enforce it in more effective and easy-to-use ways? We develop…

Machine Learning · Computer Science 2018-10-23 Nitin Bansal , Xiaohan Chen , Zhangyang Wang

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often…

Machine Learning · Computer Science 2025-11-04 Yingxu Wang , Nan Yin , Mingyan Xiao , Xinhao Yi , Siwei Liu , Shangsong Liang

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…

Machine Learning · Statistics 2018-05-24 Ziv Aharoni , Gal Rattner , Haim Permuter

Pretrained Graph Neural Networks have been widely adopted for various molecular property prediction tasks. Despite their ability to encode structural and relational features of molecules, traditional fine-tuning of such pretrained GNNs on…

Machine Learning · Computer Science 2024-01-30 Vishal Dey , Xia Ning