Group invariant scattering
From MaRDI portal
Abstract: This paper constructs translation invariant operators on L2(R^d), which are Lipschitz continuous to the action of diffeomorphisms. A scattering propagator is a path ordered product of non-linear and non-commuting operators, each of which computes the modulus of a wavelet transform. A local integration defines a windowed scattering transform, which is proved to be Lipschitz continuous to the action of diffeomorphisms. As the window size increases, it converges to a wavelet scattering transform which is translation invariant. Scattering coefficients also provide representations of stationary processes. Expected values depend upon high order moments and can discriminate processes having the same power spectrum. Scattering operators are extended on L2 (G), where G is a compact Lie group, and are invariant under the action of G. Combining a scattering on L2(R^d) and on Ld (SO(d)) defines a translation and rotation invariant scattering on L2(R^d).
Recommendations
- Rotationally invariant time-frequency scattering transforms
- The Scattering Transform
- Complete set of translation invariant measurements with Lipschitz bounds
- Analysis of time-frequency scattering transforms
- The properties of expected scattering and averaged scattering and their applications to texture classification
Cites work
- Band-limited localized Parseval frames and Besov spaces on compact homogeneous manifolds
- Fourier integral operators. I
- scientific article; zbMATH DE number 50289 (Why is no real title available?)
- scientific article; zbMATH DE number 2107182 (Why is no real title available?)
- Local Geometry of Deformable Templates
- Multiscale Representations for Manifold-Valued Data
- On contraction analysis for non-linear systems
- Opérateurs de Calderón-Zygmund, fonctions para-accrétives et interpolation. (Calderón-Zygmund operators, para-accretive functions and interpolation)
- Topics in Harmonic Analysis Related to the Littlewood-Paley Theory. (AM-63)
Cited in
(95)- Observable dictionary learning for high-dimensional statistical inference
- An effective region force for some variational models for learning and clustering
- Parsimonious representation of nonlinear dynamical systems through manifold learning: a chemotaxis case study
- On the convergence of formally diverging neural net-based classifiers
- Gabor neural networks with proven approximation properties
- The structure of group preserving operators
- Fully hyperbolic convolutional neural networks
- Convolutional spectral kernel learning with generalization guarantees
- Wavelet scattering transform and ensemble methods for side-channel analysis
- Neural network identifiability for a family of sigmoidal nonlinearities
- Universal approximations of invariant maps by neural networks
- Asymptotic analysis of higher-order scattering transform of Gaussian processes
- The signed cumulative distribution transform for 1-D signal analysis and classification
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Graph convolutional neural networks via scattering
- Approximation by group invariant subspaces
- Affine symmetries and neural network identifiability
- Rotationally invariant time-frequency scattering transforms
- Stable phase retrieval in infinite dimensions
- Multiscale sparse microcanonical models
- Intermittent process analysis with scattering moments
- Left-invariant evolutions of wavelet transforms on the similitude group
- Nonlinear phase unwinding of functions
- Analysis of time-frequency scattering transforms
- Sampling, splines and frames on compact manifolds
- Applied harmonic analysis and data science. Abstracts from the workshop held November 28 -- December 4, 2021 (hybrid meeting)
- Singular value perturbation and deep network optimization
- Unsupervised learning of invariant representations
- Left invariant evolution equations on Gabor transforms
- Data-Driven Reduction for a Class of Multiscale Fast-Slow Stochastic Dynamical Systems
- Explore Intrinsic Geometry of Sleep Dynamics and Predict Sleep Stage by Unsupervised Learning Techniques
- Carrier frequencies, holomorphy, and unwinding
- Deep Haar scattering networks
- On invariance and selectivity in representation learning
- Group invariance, stability to deformations, and complexity of deep convolutional representations
- Convolutional neural networks analyzed via convolutional sparse coding
- Lipschitz properties for deep convolutional networks
- Deep convolutional framelets: a general deep learning framework for inverse problems
- Average sampling and space-frequency localized frames on bounded domains
- Occlusion robust face recognition with scattering operator in gradient domain
- Geometric space-frequency analysis on manifolds
- Stability for the training of deep neural networks and other classifiers
- scientific article; zbMATH DE number 7625171 (Why is no real title available?)
- Bioinspired Random Projections for Robust, Sparse Classification
- Prevalence of neural collapse during the terminal phase of deep learning training
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Product formalisms for measures on spaces with binary tree structures: representation, visualization, and multiscale noise
- Convolutional Neural Networks in Phase Space and Inverse Problems
- The properties of expected scattering and averaged scattering and their applications to texture classification
- Phase-Space Sketching for Crystal Image Analysis Based on Synchrosqueezed Transforms
- Solving inverse problems using data-driven models
- Continuous piecewise affine transformation for image registration
- Deep convolutional neural networks for image classification: a comprehensive review
- Wavelet Scattering Regression of Quantum Chemical Energies
- Weak lensing trispectrum and Kurt-spectra
- The Scattering Transform
- Monogenic wavelet scattering network for texture image classification
- Lie PCA: density estimation for symmetric manifolds
- Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms
- Approximation Analysis of Convolutional Neural Networks
- Wavelet-packets for deepfake image analysis and detection
- Central and Noncentral Limit Theorems Arising from the Scattering Transform and Its Neural Activation Generalization
- Mallat scattering transformation based surrogate for magnetohydrodynamics
- Stable separation of orbits for finite abelian group actions
- Geometric scattering on measure spaces
- On the finite representation of linear group equivariant operators via permutant measures
- Stability of the scattering transform for deformations with minimal regularity
- Asymptotic Links between Signal Processing, Acoustic Metamaterials, and Biology
- On generalizations of the nonwindowed scattering transform
- When scattering transform meets non-Gaussian random processes, a double scaling limit result
- Towards a bilipschitz invariant theory
- Riesz feature representation: scale equivariant scattering network for classification tasks
- Frames and system of translates of Hilbert \(C^\ast\)-module valued functions
- Constant rank factorisations of smooth maps, with applications to sonar
- Convergence rate analysis in limit theorems for nonlinear functionals of the second Wiener chaos
- Bernhard Riemann, the ear, and an atom of consciousness
- Gaussian approximation for the moving averaged modulus wavelet transform and its variants
- Scale dependencies and self-similar models with wavelet scattering spectra
- Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces
- Hierarchic flows to estimate and sample high-dimensional probabilities
- Manifold filter-combine networks
- Integrating subdivision schemes into SVM for improved signal classification
- The theory of deep convolutional neural networks and a data approximation problem based on the fractional Fourier transform
- Generalized moduli of continuity under irregular or random deformations via multiscale analysis
- Mathematical imaging and surface processing. Abstracts from the workshop held February 2--7, 2025
- Energy propagation in scattering convolution networks can be arbitrarily slow
- Group-invariant max filtering
- Generalizing geometric nonwindowed scattering transforms on compact Riemannian manifolds
- A scattering transform for graphs based on heat semigroups, with an application for the detection of anomalies in positive time series with underlying periodicities
- A rainbow in deep network black boxes
- Fractal properties of 4-point interpolatory subdivision schemes and wavelet scattering transform for signal classification
- Multiscale Hodge scattering networks for data analysis
- A novel statistical approach to analyze image classification
- Wavelet-based Hurst exponent estimation
- Complete set of translation invariant measurements with Lipschitz bounds
This page was built for publication: Group invariant scattering
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2911046)
