English
Related papers

Related papers: The High Cost of Data Augmentation for Learning Eq…

200 papers

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…

Computer Vision and Pattern Recognition · Computer Science 2017-10-31 Toan Tran , Trung Pham , Gustavo Carneiro , Lyle Palmer , Ian Reid

Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to use augmented data. In this paper, we take a step in this…

Machine Learning · Computer Science 2022-06-17 Shuo Yang , Yijun Dong , Rachel Ward , Inderjit S. Dhillon , Sujay Sanghavi , Qi Lei

Noether's theorem is reviewed with a particular focus on an intermediate step between global and local gauge and coordinate transformations, namely linear transformations. We rederive the well known result that global symmetry leads to…

General Relativity and Quantum Cosmology · Physics 2007-05-23 M. Leclerc

A general approach is presented for quantizing a metric nonlinear system on a manifold of constant curvature. It makes use of a curvature dependent procedure which relies on determining Noether symmetries from the metric. The curvature of…

Mathematical Physics · Physics 2015-06-19 Paul Bracken

Persistent homology is a popular tool in Topological Data Analysis. It provides numerical characteristics of data sets which reflect global geometric properties. In order to be useful in practice, for example for feature generation in…

Computational Geometry · Computer Science 2020-02-17 Boris Goldfarb

The relation between symmetries and local conservation laws, known as Noether's theorem, plays an important role in modern theoretical physics. As a discrete analog of the differentiable physical system, a good numerical scheme should admit…

Computational Physics · Physics 2019-04-09 Qiang Chen , Xiaojun Hao , Chuanchuan Wang , Xiaoyang Wang , Xiang Chen , Lifei Geng

This paper is devoted to studying symmetries of certain kinds of k-cosymplectic Hamiltonian systems in first-order classical field theories. Thus, we introduce a particular class of symmetries and study the problem of associating…

Mathematical Physics · Physics 2015-12-15 J. C. Marrero , N. Román-Roy , M. Salgado , S. Vilariño

Approximation using Fourier features is a popular technique for scaling kernel methods to large-scale problems, with myriad applications in machine learning and statistics. This method replaces the integral representation of a…

Machine Learning · Statistics 2024-08-26 Ayoub Belhadji , Qianyu Julie Zhu , Youssef Marzouk

In the framework of phantom quintessence cosmology, we use the Noether Symmetry Approach to obtain general exact solutions for the cosmological equations. This result is achieved by the quintessential (phantom) potential determined by the…

Cosmology and Nongalactic Astrophysics · Physics 2010-04-30 S. Capozziello , E. Piedipalumbo , C. Rubano , P. Scudellaro

The existence of a Noether symmetry for a given minisuperspace cosmological model is a sort of selection rule to recover classical behaviours in cosmic evolution since oscillatory regimes for the wave function of the universe come out. The…

General Relativity and Quantum Cosmology · Physics 2015-06-25 S. Capozziello , G. Lambiase

Noether's theorem relates constants of motion to the symmetries of the system. Here we investigate a manifestation of Noether's theorem in non-Hermitian systems, where the inner product is defined differently from quantum mechanics. In this…

Quantum Physics · Physics 2021-01-25 Jose D. H. Rivero , Li Ge

We find exact cosmological solutions when the Newton parameter and the cosmological term are dynamically evolving in a renormalization-group improved Hamiltonian approach. In our derivation we use the Noether symmetry approach, leading to…

General Relativity and Quantum Cosmology · Physics 2008-11-26 Alfio Bonanno , Giampiero Esposito , Claudio Rubano , Paolo Scudellaro

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

We consider the geometric numerical integration of Hamiltonian systems subject to both equality and "hard" inequality constraints. As in the standard geometric integration setting, we target long-term structure preservation. We…

Numerical Analysis · Mathematics 2011-06-02 Danny M. Kaufman , Dinesh K. Pai

In this paper, a complete analysis of symmetries and conservation laws for the charged squashed Kaluza--Klein black hole spacetime in a Riemannian space is discussed. First, a comprehensive group analysis of the underlying space-time metric…

Differential Geometry · Mathematics 2014-08-11 Rohollah Bakhshandeh Chamazkoti

Symmetry plays a fundamental role in understanding natural phenomena and mathematical structures. This work develops a comprehensive theory for studying the persistent symmetries and degree of asymmetry of finite point configurations over…

Algebraic Topology · Mathematics 2025-08-12 Jian Liu , Dong Chen , Guo-Wei Wei

Data augmentation is a technique to improve the generalization ability of machine learning methods by increasing the size of the dataset. However, since every augmentation method is not equally effective for every dataset, you need to…

Machine Learning · Computer Science 2022-05-31 Daisuke Oba , Shinnosuke Matsuo , Brian Kenji Iwana

This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symplectic subspaces for…

Numerical Analysis · Mathematics 2023-08-25 Harsh Sharma , Hongliang Mu , Patrick Buchfink , Rudy Geelen , Silke Glas , Boris Kramer

We discuss the relation between symmetries and conservation laws in the realm of classical field theories based on the Hamiltonian constraint. In this approach, spacetime positions and field values are treated on equal footing, and a…

Mathematical Physics · Physics 2016-04-15 Vaclav Zatloukal

Noether's theorem provides a powerful link between continuous symmetries and conserved quantities for systems governed by some variational principle. Perhaps unfortunately, most dynamical systems of interest in neuroscience and artificial…

Machine Learning · Computer Science 2025-04-15 John J. Vastola
‹ Prev 1 3 4 5 6 7 10 Next ›