The paper characterizes strong Hamel functions using symmetries and proves their preservation properties.
problem Characterizing strong Hamel functions and their symmetries in Finsler spaces.
method Analyzing geodesic spray, strong dual symmetries, and strong dynamical symmetries.
result Strong Hamel functions can be characterized in terms of strong dual symmetries and strong dynamical symmetries.
Symmetry of neural network densities can be determined from correlation functions.
problem Determining symmetries of neural network densities without knowing the density itself.
method Symmetry-via-duality approach using invariance properties of correlation functions.
result Symmetries of neural network densities can be determined via dual computations of correlation functions.
Symmetry in loss functions constrains model parameters, leading to specific learning outcomes.
problem Understanding and leveraging symmetries in neural networks to improve learning outcomes.
method Analyzing the impact of loss function symmetries on model parameters and learning behavior.
result Mirror-reflection symmetries in loss functions lead to constraints on model parameters, influencing learning outcomes.
Exploits symmetries for efficient reinforcement learning with deep networks.
problem Efficient function approximation in reinforcement learning with large data requirements.
method Detects symmetries using reward trails, incorporates them for functional approximation.
result Significant improvement in learning performance by utilizing symmetry information.
New findings on hidden symmetries in ReLU networks.
problem Understanding the redundancy and symmetries in ReLU network parameter space.
method Analyzing parameter settings and function classes for various network architectures.
result For certain network architectures, there are no hidden symmetries.
Symmetric critical points lead to symmetry breaking in neural networks.
problem Understanding symmetry in critical points of invariant functions.
method Analyzing the symmetry of critical points and their neighbors in invariant nonconvex functions.
result Symmetric critical points in invariant nonconvex functions are generically followed by symmetry breaking adjacent points.
Symmetries of Poisson manifolds are in general quantized just to symmetries up to homotopy of the quantized algebra of functions. It is therefore interesting to study symmetries up to homotopy of Poisson manifolds. We notice that they are equivalent to Poisson principal bundles and describe their quantization to symmet…
The paper classifies quantizable functions and explores symmetry in quantization methods.
problem Classifying quantizable functions and understanding symmetry in quantization methods.
method Deformation quantization and geometric quantization methods are compared and classified.
result Formal quantizable functions are of a specific form and relate to Hamiltonian Killing vector fields.
Study shows most hyperbolic knot complements lack hidden symmetries.
problem Proving most knot complements lack hidden symmetries.
method Using rational functions on varieties associated to a link.
result Most knot complements lack hidden symmetries.
New formulae derived for conformal symmetry breaking operators.
problem Understanding conformal symmetry breaking operators.
method Bernstein-Sato identities for distribution kernels.
result New formulae for conformal symmetry breaking differential operators.
Study proves radial symmetry in convex cones using subharmonic functions.
problem Proving radial symmetry in convex cones with boundary conditions.
method Using maximum principle and integral identities for subharmonic functions.
result Proves radial symmetry and Serrin-type results for partially overdetermined problems.
New variational principle found for PDEs with symmetries and conservation laws.
problem Finding variational principles for PDEs with symmetries and conservation laws.
method Proving existence of a variational principle for PDEs with symmetries and conservation laws.
result A differential equation with sufficient symmetries and conservation laws leads to a variational functional.
Discusses a new divergence function in information geometry.
problem Symmetry properties of divergence functions in information geometry.
method Analyzes a recently introduced canonical divergence function.
result Outlines open problems regarding symmetry properties.
The study explores Hesse manifolds and their symmetries in multifield cosmological models.
problem Understanding symmetries in multifield cosmological models.
method Analyzes Hesse functions and their properties on Riemannian manifolds.
result Complete Hesse manifolds are characterized by their index and are hyperbolic.
Functional dimension varies in ReLU networks, with implications for symmetry and connectivity.
problem Understanding the functional dimension of ReLU neural networks.
method Careful definition and analysis of functional dimension, study of quotient space and fibers.
result Functional dimension is inhomogeneous and can be non-constant, with implications for symmetry and connectivity.
In the framework of Galilei classical mechanics (i.e., general relativistic classical mechanics on a spacetime with absolute time) developed by Jadczyk and Modugno, we analyse systematically the relations between symmetries of the geometric objects. We show that the (holonomic) infinitesimal symmetries of the cosymplec…
Quantum field theory explains machine learning symmetries.
problem Machine learning symmetries and convergence issues.
method Formulated a gauge theory of `charged' embedding vectors in time series models.
result Making the loss function gauge invariant speeds up convergence.
In this paper, a symmetry classification of a (2+1)-nonlinear wave equation utt−f(u)(uxx+uyy)=0 where f(u) is a smooth function on u, using Lie group method, is given. The basic infinitesimal method for calculating symmetry groups is presented, and used to determine the general symmetry group of this $…
An impossibility result shows limitations in learning symmetries and equivariant functions.
problem Learning symmetries and equivariant functions simultaneously is impossible under certain conditions.
method Careful study of approximation for groups and semigroups, analysis of neural networks.
result Linearly equivariant networks can be used to learn equivariant functions, but group-convolutional networks have limitations.
Symmetry-regularized Neural ODEs improve model stability and interpretability.
problem Improving the stability and physical interpretability of Neural ODEs.
method Integrating Lie symmetries and conservation laws into the loss function.
result Symmetry-regularized Neural ODEs enhance model stability and interpretability.
Study biharmonic functions on vector bundles with spherical symmetry.
problem Investigate biharmonic functions on vector bundles with spherically symmetric metrics.
method Analyze vertical lifts and radial functions of functions on vector bundle manifolds.
result Construct an infinite two-parameter family of proper biharmonic functions.
A reduction method of ODEs not possessing Lie point symmetries makes use of the so called λ-symmetries (C. Muriel and J. L. Romero, \emph{IMA J. Appl. Math.} \textbf{66}, 111-125, 2001). The notion of covering for an ODE Y is used here to recover λ-symmetries of Y as nonlocal symmetries. In …
New findings on neural network identifiability using affine symmetries.
problem Identifying all neural networks that produce a given function.
method Examined affine symmetries of nonlinearities and their impact on neural network identifiability.
result Symmetries can be used to find a rich set of networks giving rise to the same function, except for a special case.
Noether's framework reveals symmetry-breaking in neural networks.
problem Understanding the role of symmetry breaking in neural networks.
method Developed a theoretical framework using Lagrangian mechanics.
result Identified 'kinetic symmetry breaking' and its effect on learning dynamics.
Classifies charge-3 monopoles with symmetry, identifying new spectral curves.
problem Classifying charge-3 monopoles with symmetry.
method Constructing Nahm data and identifying spectral curves with elliptic quotients.
result New monopole spectral curves with D6 and V4 symmetry identified. New method uses scalars to approximate physics functions.
problem Designing neural networks that respect physical symmetries.
method Parameterizing polynomial functions equivariant to various symmetries using scalars.
result Universal approximation of polynomial functions under various symmetries using scalars.
Unified framework for enforcing, discovering, and promoting symmetry in machine learning.
problem Symmetry in machine learning models and data.
method Unified mathematical framework using Lie derivatives, convex regularization, and nuclear norm relaxation.
result Unified approach to symmetry in machine learning tasks.
The nonlinear sigma model with gravitino exhibits symmetries and conservation laws.
problem Exploring symmetries and conservation laws in a nonlinear sigma model with gravitino.
method Geometric analysis of rescaled conformal transformations, super Weyl transformations, and diffeomorphisms.
result The model possesses degenerate super symmetry leading to geometric interpretations of energy-momentum tensor and supercurrent.
New approach to symmetries in teleparallel geometries with non-trivial isotropy groups.
problem Determining symmetries with non-trivial isotropy groups in teleparallel geometries.
method Introducing a frame-based approach to find the most general Riemann-Cartan geometries that admit a given symmetry group.
result Determine the most general geometries with minimal arbitrary functions for specific symmetry groups.
Efficient MCMC sampling in Bayesian neural networks by exploiting symmetries.
problem Challenges in Bayesian inference due to high-dimensional, multi-modal posterior density landscapes.
method Exploiting symmetries in the posterior landscape to restrict the parameter space and derive an upper bound on Monte Carlo chains.
result Efficient sampling is possible, offering a promising path for accurate uncertainty quantification in deep learning.
Study on special symmetries in biwarped product 3-manifolds.
problem Characterizing Killing vector fields on biwarped product-type 3-manifolds.
method Derived system of equations for Killing fields and described their structure.
result Families of solutions found, including explicit examples.
Develops a theory for equivariant networks with partial domain symmetry.
problem Limited analysis of equivariant networks with partial domain symmetry.
method Proposes pointwise definitions of correct, incorrect, and extrinsic equivariance.
result Establishes error lower bounds for networks with partial symmetry.
We use Lie symmetry methods to price certain types of barrier options. Usually Lie symmetry methods cannot be used to solve the Black-Scholes equation for options because the function defining the maturity condition for an option is not smooth. However, for barrier options, this restriction can be accommodated and a sy…
We give a complete classification of intertwining operators (symmetry breaking operators) between spherical principal series representations of G=O(n+1,1) and G'=O(n,1). We construct three meromorphic families of the symmetry breaking operators, and find their distribution kernels and their residues at all poles explic…
Method improves deep learning models for datasets with mixed approximate symmetries.
problem Improving deep learning models for datasets with mixed approximate symmetries.
method Regularizer-based approach to build models for datasets with mixed approximate symmetries.
result Our method achieves better accuracy than prior approaches while discovering the approximate symmetry levels correctly.
New deep learning method preserves orientation in shape matching.
problem Symmetry issues in shape matching.
method Orientation-aware functional maps using complex functional representations and DiffusionNet.
result Stable correspondence predictions with robust orientation preservation.
Method discovers symmetries in data with neural networks.
problem Discovering symmetries in high-dimensional data.
method Fully connected neural networks trained with a loss function for symmetry.
result Generators for symmetries in latent space.
Study proves symmetry of bounded domains in Riemannian manifolds.
problem Symmetry of bounded domains in Riemannian manifolds.
method Integral identities and P-function method. result Equality implies the domain is isometric to a Euclidean ball.
Study reveals different types of critical points in shallow neural networks.
problem Optimization challenges in two-layer ReLU networks with symmetry.
method Symmetry analysis, bifurcation theory, and geometric group actions.
result Different types of spurious minima have distinct loss behavior.
This paper characterizes Lie symmetries for a general Lienard-type equation.
problem Characterizing Lie symmetries for a general Lienard-type equation.
method Analyzing the Lie symmetry group of the general Lienard-type equation u¨=∑k=0nfku˙k for n≥4. result The paper provides a condition for the existence of another Lie symmetry and characterizes when the equation admits such symmetries.
New method breaks symmetry in neural networks, improving sample efficiency.
problem Symmetry in neural networks limits their ability to learn unique features.
method Introduces 'relaxed equivariance' to overcome symmetry limitations.
result Equivariant multilayer perceptrons (E-MLPs) can now break symmetry at the sample level.
Using the symmetry group theory of second order PDEs, one finds the symmetry group associated to Tzitzeica surfaces partial differential equation. One studies the inverse problem and one shows that the Tzitzeica surfaces PDE is an Euler-Lagrange equation. One determines the variational symmetry group of the associated …
New method for invariant neural networks using probabilistic symmetries.
problem Improving neural network performance in data-scarce, non-i.i.d., or unsupervised settings.
method Characterizing neural network structures invariant under compact group actions using probabilistic symmetry.
result Established a link between functional and probabilistic symmetry, yielding generative representations of invariant distributions.
Remove symmetries to improve model optimization and performance.
problem Symmetries in loss functions trap models in low-capacity states, hindering training and optimization.
method Proposes syre, a simple algorithm to remove symmetries in neural networks.
result Removing symmetries correlates well with improved optimization and performance.
The paper explores Kähler-Ricci solitons with maximal symmetry in complex dimension two.
problem Characterizing Kähler-Ricci solitons with maximal symmetry.
method Analyzes the isometry group and uses cohomogeneity one and Sasakian models.
result In complex dimension two, every non-trivial gradient Kähler-Ricci soliton has maximal symmetry.
SymPE breaks symmetries in equivariant networks, improving performance across various tasks.
problem Equivariant networks cannot break symmetries, leading to poor performance in tasks with symmetrical inputs.
method Novel equivariant conditional distributions and randomized canonicalization.
result SymPE significantly improves performance of group-equivariant and graph neural networks.
In this paper, we present the point symmetry group of three-dimensional homogeneous Helmholtz equation, when we consider the cylindrical coordinate system. In continuation, we present a complete set of functionally independent invariants of the equation along with the form of the general solution provided by these inva…
The paper extends Noether's theorem to contact systems, finding dissipated quantities instead of conserved ones.
problem Noether's theorem for contact systems does not produce conserved quantities.
method Classification of infinitesimal symmetries in contact Lagrangian systems, leading to dissipated quantities.
result Infinitesimal symmetries in contact dynamics lead to dissipated quantities rather than conserved ones.