Probabilistic symmetries and invariant neural networks

zbMATH Open1502.62092arXiv1901.06082MaRDI QIDQ4969154FDOQ4969154

Authors: Benjamin Bloem-Reddy, Yee Whye Teh 

Publication date: 5 October 2020

Full work available at URL: https://arxiv.org/abs/1901.06082

Recommendations

• Universal approximations of invariant maps by neural networks
• The complexity of explaining neural networks through (group) invariants
• The complexity of explaining neural networks through (group) invariants
• A unifying framework for invariant pattern recognition
• Representation theory and invariant neural networks

zbMATH Keywords

exchangeabilityinvariancesufficiencyadequacyconvolutional neural networksequivariancegraph neural networksneural architecturesprobabilistic symmetry

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45) Sufficient statistics and fields (62B05) Exchangeability for stochastic processes (60G09)

Cites Work

• Practical graph isomorphism. II.
• Group invariance, stability to deformations, and complexity of deep convolutional representations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Large networks and graph limits
• Testing Statistical Hypotheses
• Title not available (Why is that?)
• Bayesian optimization for likelihood-free inference of simulator-based statistical models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Group Invariance in Statistical Inference
• Distributions of maximal invariants using quotient measures
• Title not available (Why is that?)
• Probability and stochastics.
• A dozen de Finetti-style results in search of a theory
• De Finetti's theorem for Markov chains
• Finite exchangeable sequences
• Finite forms of de Finetti's theorem on exchangeability
• Ferguson distributions via Polya urn schemes
• Sample sizes for threshold networks with equivalences
• Exchangeability, predictive distributions and parametric models
• Information Theory and Statistical Mechanics
• Application of the Radon-Nikodym Theorem to the Theory of Sufficient Statistics
• Multilayer feedforward networks are universal approximators
• Theory of statistics
• Symmetric Measures on Cartesian Products
• Title not available (Why is that?)
• Approximation by superpositions of a sigmoidal function
• Title not available (Why is that?)
• Exchangeable random measures
• Representation theory and invariant neural networks
• Extremal families and systems of sufficient statistics
• Probabilistic Symmetries and Invariance Principles
• Title not available (Why is that?)
• Bayesian nonparametric analysis of reversible Markov chains
• Title not available (Why is that?)
• Sufficiency and Statistical Decision Functions
• Title not available (Why is that?)
• Invariants Under Mixing Which Generalize de Finetti's Theorem: Continuous Time Parameter
• Nonparametric network models for link prediction
• Invariants Under Mixing which Generalize de Finetti's Theorem
• Invariance and independence in multivariate distribution theory
• The Relationship Between Sufficiency and Invariance with Applications in Sequential Analysis
• Title not available (Why is that?)
• Multiscale sparse microcanonical models
• Random measures, theory and applications
• Adequate Subfields and Sufficiency
• Title not available (Why is that?)
• Edge exchangeable models for interaction networks
• A FACTORISATION THEOREM FOR ADEQUATE STATISTICS

Cited In (13)

• Invariance, Encodings, and Generalization: Learning Identity Effects With Neural Networks
• The complexity of explaining neural networks through (group) invariants
• Universal approximations of invariant maps by neural networks
• Iterative SE(3)-transformers
• Title not available (Why is that?)
• A de Finetti-type representation of joint hierarchically exchange
• Optimal Dorfman group testing for symmetric distributions
• Group-Invariant Tensor Train Networks for Supervised Learning
• What is... an Equivariant Neural Network?
• Gauge symmetry and neural networks
• The complexity of explaining neural networks through (group) invariants
• Neural networks enforcing physical symmetries in nonlinear dynamical lattices: the case example of the Ablowitz-Ladik model
• On the finite representation of linear group equivariant operators via permutant measures

Uses Software

• GAP
• Mathematica
• Theano
• TensorFlow
• PyTorch
• Tensor2Tensor

This page was built for publication: Probabilistic symmetries and invariant neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969154)