English
Related papers

Related papers: Algebraic Approach to Ridge-Regularized Mean Squar…

200 papers

Neural Networks (NN) with ReLU activation functions are used to model multiparametric quadratic optimization problems (mp-QP) in diverse engineering applications. Researchers have suggested leveraging the piecewise affine property of deep…

Optimization and Control · Mathematics 2025-10-31 Fuat Can Beylunioglu , Mehrdad Pirnia , P. Robert Duimering

Implicit Neural Representations (INRs) have emerged as a powerful tool for geometric representation, yet their suitability for physics-based simulation remains underexplored. While metrics like Hausdorff distance quantify surface…

Computational Engineering, Finance, and Science · Computer Science 2026-02-03 Samundra Karki , Adarsh Krishnamurthy , Baskar Ganapathysubramanian

The robustness of the kernel recursive least square (KRLS) algorithm has recently been improved by combining them with more robust information-theoretic learning criteria, such as minimum error entropy (MEE) and generalized MEE (GMEE),…

Information Theory · Computer Science 2023-09-07 Jiacheng He , Gang Wang , Kun Zhang , Shan Zhong , Bei Peng

Kernel methods, particularly kernel ridge regression (KRR), are time-proven, powerful nonparametric regression techniques known for their rich capacity, analytical simplicity, and computational tractability. The analysis of their predictive…

Statistics Theory · Mathematics 2025-09-23 Xin Bing , Xin He , Chao Wang

Distributed LLM inference requires careful coordination of parallelization strategies across hundreds to thousands of NPUs to meet production SLOs. Current systems like Megatron-LM rely on static heuristics that separately configure…

Machine Learning · Computer Science 2025-09-03 Ruokai Yin , Sattwik Deb Mishra , Xuan Zuo , Hokchhay Tann , Preyas Shah , Apala Guha

The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency…

Sound · Computer Science 2025-11-11 Zixuan Li , Xueliang Zhang , Changjiang Zhao , Shuai Gao , Lei Miao , Zhipeng Yan , Ying Sun , Chong Zhu

We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue that such a correction is a useful way to provide feedback to…

Machine Learning · Computer Science 2018-09-03 Xin Zhang , Armando Solar-Lezama , Rishabh Singh

idely used recurrent units, including Long-short Term Memory (LSTM) and the Gated Recurrent Unit (GRU), perform well on natural language tasks, but their ability to learn structured representations is still questionable. Exploiting reduced…

Neural and Evolutionary Computing · Computer Science 2019-11-06 Shuai Tang , Paul Smolensky , Virginia R. de Sa

Gradient descent (GD) type optimization methods are the standard instrument to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Despite the great success of GD type optimization methods in numerical…

Optimization and Control · Mathematics 2022-12-29 Arnulf Jentzen , Adrian Riekert

Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Michael Baltaxe , Dan Levi , Sagie Benaim

We introduce an $r-$adaptive algorithm to solve Partial Differential Equations using a Deep Neural Network. The proposed method restricts to tensor product meshes and optimizes the boundary node locations in one dimension, from which we…

Numerical Analysis · Mathematics 2022-10-21 Ángel J. Omella , David Pardo

With the recent emergence of mixed precision hardware, there has been a renewed interest in its use for solving numerical linear algebra problems fast and accurately. The solution of total least squares problems, i.e., solving $\min_{E,r}…

Numerical Analysis · Mathematics 2023-09-14 Eda Oktay , Erin Carson

Kernel ridge regression, KRR, is a generalization of linear ridge regression that is non-linear in the data, but linear in the model parameters. Here, we introduce an equivalent formulation of the objective function of KRR, which opens up…

Machine Learning · Statistics 2025-03-10 Oskar Allerbo

Choosing an appropriate learning rate remains a key challenge in scaling depth of modern deep networks. The classical maximal update parameterization ($\mu$P) enforces a fixed per-layer update magnitude, which is well suited to homogeneous…

Machine Learning · Computer Science 2025-12-01 Haosong Zhang , Shenxi Wu , Yichi Zhang , Xi Chen , Wei Lin

22. Shortening acquisition time and reducing the motion-artifact are two of the most critical issues in MRI. As a promising solution, high-quality MRI image restoration provides a new approach to achieve higher resolution without costing…

Image and Video Processing · Electrical Eng. & Systems 2021-02-02 Hao Li , Jianan Liu

A fully tensorial theoretical framework for hypercomplex-valued neural networks is presented. The proposed approach enables neural network architectures to operate on data defined over arbitrary finite-dimensional algebras. The central…

Machine Learning · Computer Science 2026-01-27 Agnieszka Niemczynowicz , Radosław Antoni Kycia

We introduced the least-squares ReLU neural network (LSNN) method for solving the linear advection-reaction problem with discontinuous solution and showed that the method outperforms mesh-based numerical methods in terms of the number of…

Numerical Analysis · Mathematics 2022-01-26 Zhiqiang Cai , Jingshuang Chen , Min Liu

Subsampling is a popular approach to alleviating the computational burden for analyzing massive datasets. Recent efforts have been devoted to various statistical models without explicit regularization. In this paper, we develop an efficient…

Methodology · Statistics 2022-04-12 Yunlu Chen , Nan Zhang

We introduce the "inverse square root linear unit" (ISRLU) to speed up learning in deep neural networks. ISRLU has better performance than ELU but has many of the same benefits. ISRLU and ELU have similar curves and characteristics. Both…

Machine Learning · Computer Science 2017-11-13 Brad Carlile , Guy Delamarter , Paul Kinney , Akiko Marti , Brian Whitney

Many real world data sets exhibit an embedding of low-dimensional structure in a high-dimensional manifold. Examples include images, videos and internet traffic data. It is of great significance to reduce the storage requirements and…

Methodology · Statistics 2015-06-05 Yuejie Chi , Yonina C. Eldar , Robert Calderbank