Symmetry & Critical Points

• URL: http://arxiv.org/abs/2408.14445v1
• Date: Mon, 26 Aug 2024 17:36:51 GMT
• Title: Symmetry & Critical Points
• Authors: Yossi Arjevani,
• Abstract summary: Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists adjacent to it are generic.
• Score: 7.23389716633927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists, those adjacent to it are generically symmetry breaking. This mathematical mechanism is shown to carry important implications for our ability to efficiently minimize invariant nonconvex functions, in particular those associated with neural networks.

Related papers

• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof [50.49582712378289]
  We investigate the impact of neural parameter symmetries by introducing new neural network architectures. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries.
  arXiv  Detail & Related papers  (2024-05-30T16:32:31Z)
• Dimension matters: precision and incompatibility in multi-parameter quantum estimation models [44.99833362998488]
  We study the role of probe dimension in determining the bounds of precision in quantum estimation problems. We also critically examine the performance of the so-called incompatibility (AI) in characterizing the difference between the Holevo-Cram'er-Rao bound and the Symmetric Logarithmic Derivative (SLD) one.
  arXiv  Detail & Related papers  (2024-03-11T18:59:56Z)
• Symmetry-restricted quantum circuits are still well-behaved [45.89137831674385]
  We show that quantum circuits restricted by a symmetry inherit the properties of the whole special unitary group $SU(2n)$. It extends prior work on symmetric states to the operators and shows that the operator space follows the same structure as the state space.
  arXiv  Detail & Related papers  (2024-02-26T06:23:39Z)
• Symmetry Breaking and Equivariant Neural Networks [17.740760773905986]
  We introduce a novel notion of'relaxed equiinjection' We show how to incorporate this relaxation into equivariant multilayer perceptronrons (E-MLPs) The relevance of symmetry breaking is then discussed in various application domains.
  arXiv  Detail & Related papers  (2023-12-14T15:06:48Z)
• Lie Point Symmetry and Physics Informed Networks [59.56218517113066]
  We propose a loss function that informs the network about Lie point symmetries in the same way that PINN models try to enforce the underlying PDE through a loss function. Our symmetry loss ensures that the infinitesimal generators of the Lie group conserve the PDE solutions. Empirical evaluations indicate that the inductive bias introduced by the Lie point symmetries of the PDEs greatly boosts the sample efficiency of PINNs.
  arXiv  Detail & Related papers  (2023-11-07T19:07:16Z)
• A universal formula for the entanglement asymmetry of matrix product states [0.0]
  We provide a universal formula for the entanglement asymmetry of matrix product states with finite bond dimension. We show that the entanglement asymmetry of any compact -- discrete or continuous -- group depends only on the symmetry breaking pattern, and is not related to any other microscopic features.
  arXiv  Detail & Related papers  (2023-10-03T11:15:19Z)
• Towards Antisymmetric Neural Ansatz Separation [48.80300074254758]
  We study separations between two fundamental models of antisymmetric functions, that is, functions $f$ of the form $f(x_sigma(1), ldots, x_sigma(N)) These arise in the context of quantum chemistry, and are the basic modeling tool for wavefunctions of Fermionic systems.
  arXiv  Detail & Related papers  (2022-08-05T16:35:24Z)
• Machine-learning hidden symmetries [0.0]
  We present an automated method for finding hidden symmetries, defined as symmetries that become manifest only in a new coordinate system that must be discovered. Its core idea is to quantify asymmetry as violation of certain partial differential equations, and to numerically minimize such violation over the space of all invertible transformations, parametrized as invertible neural networks.
  arXiv  Detail & Related papers  (2021-09-20T17:55:02Z)
• Symmetry Breaking in Symmetric Tensor Decomposition [44.181747424363245]
  We consider the nonsymmetry problem associated with computing the points rank decomposition of symmetric tensors. We show that critical points the loss function is detected by standard methods.
  arXiv  Detail & Related papers  (2021-03-10T18:11:22Z)
• Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks [2.735801286587347]
  We demonstrate that symmetry equivariant neural networks uphold Curie's principle and can be used to articulate many symmetry-relevant scientific questions into simple optimization problems. We prove these properties mathematically and demonstrate them numerically by training a Euclidean symmetry equivariant neural network to learn symmetry-breaking input to deform a square into a rectangle and to generate octahedra tilting patterns in perovskites.
  arXiv  Detail & Related papers  (2020-07-04T17:24:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.