Multiscale sparse microcanonical models

DOI10.4171/MSL/7zbMath1426.62111arXiv1801.02013OpenAlexW2963431808WikidataQ127834567 ScholiaQ127834567MaRDI QIDQ2319816

Joan Bruna, Stephane Mallat

Publication date: 20 August 2019

Published in: Mathematical Statistics and Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1801.02013

zbMATH Keywords

scatteringwavelettexturemicrocanonicalmacrocanonical

Mathematics Subject Classification ID

Density estimation (62G07) Higher-dimensional and -codimensional surfaces in Euclidean and related (n)-spaces (53A07) Renormalization group methods in equilibrium statistical mechanics (82B28) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (10)

Particle gradient descent model for point process generation ⋮ Unnamed Item ⋮ Central and Noncentral Limit Theorems Arising from the Scattering Transform and Its Neural Activation Generalization ⋮ Stable separation of orbits for finite abelian group actions ⋮ Geometric scattering on measure spaces ⋮ Patch Redundancy in Images: A Statistical Testing Framework and Some Applications ⋮ Maximum entropy models from phase harmonic covariances ⋮ Complete set of translation invariant measurements with Lipschitz bounds ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Deep learning architectures for nonlinear operator functions and nonlinear inverse problems

Uses Software

• GradSamp
• Steerable pyramid
• ScatNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• From Newton to Boltzmann: hard spheres and short-range potentials
• Gibbs measures and phase transitions.
• Microcanonical distributions for lattice gases
• Introduction to the functional renormalization group
• A dozen de Finetti-style results in search of a theory
• Hamburger moment problem and maximum entropy: on the existence conditions
• Global convergence of ADMM in nonconvex nonsmooth optimization
• A probabilistic approach to the geometry of the \(\ell^n_p\)-ball
• A parametric texture model based on joint statistics of complex wavelet coefficients
• Intermittent process analysis with scattering moments
• Sard theorems for Lipschitz functions and applications in optimization
• Group Invariant Scattering
• Information Theory and Statistical Mechanics
• Graphical Models, Exponential Families, and Variational Inference
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Time evolution of large classical systems
• Wavelets and Renormalization
• Deep Scattering Spectrum
• Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
• Phase harmonic correlations and convolutional neural networks
• A Robust Gradient Sampling Algorithm for Nonsmooth, Nonconvex Optimization
• A note about the uniform distribution on the intersection of a simplex and a sphere
• Random Phase Textures: Theory and Synthesis
• Convergence of the Iterates of Descent Methods for Analytic Cost Functions
• Power spectra of random spike fields and related processes
• Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition

This page was built for publication: Multiscale sparse microcanonical models