English
Related papers

Related papers: Lorentz-Equivariance without Limitations

200 papers

Recent work has constructed neural networks that are equivariant to continuous symmetry groups such as 2D and 3D rotations. This is accomplished using explicit Lie group representations to derive the equivariant kernels and nonlinearities.…

Machine Learning · Computer Science 2022-12-08 Noah Shutty , Casimir Wierzynski

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning…

High Energy Physics - Phenomenology · Physics 2020-01-22 Sven Bollweg , Manuel Haussmann , Gregor Kasieczka , Michel Luchmann , Tilman Plehn , Jennifer Thompson

Rotation invariance is an important requirement for point shape analysis. To achieve this, current state-of-the-art methods attempt to construct the local rotation-invariant representation through learning or defining the local reference…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Yiyang Chen , Lunhao Duan , Shanshan Zhao , Changxing Ding , Dacheng Tao

The increasing data rates and complexity of detectors at the Large Hadron Collider (LHC) necessitate fast and efficient machine learning models, particularly for rapid selection of what data to store, known as triggering. Building on recent…

Instrumentation and Detectors · Physics 2025-11-05 Lino Gerlach , Elliott Kauffman , Liv Helen Våge , Isobel Ojalvo

Representation learning is a pivotal area in the field of machine learning, focusing on the development of methods to automatically discover the representations or features needed for a given task from raw data. Unlike traditional feature…

Machine Learning · Computer Science 2024-10-11 Jose Antonio Martin H. , Freddy Perozo , Manuel Lopez

Similarity metrics such as representational similarity analysis (RSA) and centered kernel alignment (CKA) have been used to compare layer-wise representations between neural networks. However, these metrics are confounded by the population…

Machine Learning · Statistics 2022-02-02 Tianyu Cui , Yogesh Kumar , Pekka Marttinen , Samuel Kaski

We present an algorithm for L1-norm kernel PCA and provide a convergence analysis for it. While an optimal solution of L2-norm kernel PCA can be obtained through matrix decomposition, finding that of L1-norm kernel PCA is not trivial due to…

Machine Learning · Statistics 2020-06-12 Cheolmin Kim , Diego Klabjan

The fixed-point logic LREC= was developed by Grohe et al. (CSL 2011) in the quest for a logic to capture all problems decidable in logarithmic space. It extends FO+C, first-order logic with counting, by an operator that formalises a limited…

Logic in Computer Science · Computer Science 2023-04-26 Steffen van Bergerem , Martin Grohe , Sandra Kiefer , Luca Oeljeklaus

In a recent article [1] we have explored alternative decompositions of the Lorentz transformation by adopting the synchronization convention of the target frame at the end and alternately at the outset. In this note we develop the…

General Physics · Physics 2008-05-21 Chandru Iyer

In this work, we propose the joint linked component analysis (joint\_LCA) for multiview data. Unlike classic methods which extract the shared components in a sequential manner, the objective of joint\_LCA is to identify the view-specific…

Machine Learning · Statistics 2024-06-18 Lin Xiao , Luo Xiao

Introducing the primed inertial coordinate system, for each inertial frame of reference, in addition to the usual inertial coordinate system, we assume that gravity-free space and time possess the Euclidean structures in the primed inertial…

General Physics · Physics 2007-05-23 Jian-Miin Liu

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on…

Computation and Language · Computer Science 2023-11-29 Yixiao Li , Yifan Yu , Chen Liang , Pengcheng He , Nikos Karampatziakis , Weizhu Chen , Tuo Zhao

Linear latent variable models such as principal component analysis (PCA), independent component analysis (ICA), canonical correlation analysis (CCA), and factor analysis (FA) identify latent directions (or loadings) either ordered or…

Machine Learning · Statistics 2023-07-13 Jesse Stevens , Daniel N. Wilke , Itumeleng Setshedi

In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Axel Klawonn , Martin Lanser , Janine Weber

In the quest to produce quantum technology, superconducting networks, working at temperatures just above absolute zero, have arisen as one of the most promising physical implementations. The precise analysis and synthesis of such circuits…

Quantum Physics · Physics 2021-04-20 Adrian Parra-Rodriguez

While Transformer-based and standard Graph Neural Networks (GNNs) have proven to be the best performers in classifying different types of jets, they require substantial computational power. We explore the scope of using a lightweight and…

High Energy Physics - Phenomenology · Physics 2026-02-23 Rajneil Baruah , Subhadeep Mondal , Sunando Kumar Patra , Satyajit Roy

Top-N recommendation is a challenging problem because complex and sparse user-item interactions should be adequately addressed to achieve high-quality recommendation results. The local latent factor approach has been successfully used with…

Information Retrieval · Computer Science 2021-03-31 Minjin Choi , Yoonki Jeong , Joonseok Lee , Jongwuk Lee

Particle localization within quantum field theory is revisited. Canonical quantization of a free scalar field theory is performed in a manifestly Lorentz covariant way with respect to an arbitrary 3-surface $\Sigma$, which is the…

High Energy Physics - Theory · Physics 2018-08-01 Matej Pavšič

We present Locally Orderless Networks (LON) and its theoretic foundation which links it to Convolutional Neural Networks (CNN), to Scale-space histograms, and measurement theory. The key elements are a regular sampling of the bias and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Jon Sporring , Peidi Xu , Jiahao Lu , François Lauze , Sune Darkner

Label Propagation (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification but LPA propagates node label information across the edges of the graph, while…

Machine Learning · Computer Science 2020-02-18 Hongwei Wang , Jure Leskovec