Identification of Shallow Neural Networks by Fewest Samples

No abstract is available for this paper.

• Publication year

  2018

• Venue

  arXiv.org

• Publication date

  2018-04-04

• Fields of study

  Mathematics, Computer Science

• Identifiers

  No identifiers available.

• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit

  2019cited by this paper
• On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition

  2018cited by this paper
• Neural Networks as Interacting Particle Systems: Asymptotic Convexity of the Loss Landscape and Universal Scaling of the Approximation Error

  2018influential reference
• Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods

  2017influential reference
• Towards Evaluating the Robustness of Neural Networks

  2016cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Interpretable Deep Neural Networks for Single-Trial EEG Classification

  2016cited by this paper
• No bad local minima: Data independent training error guarantees for multilayer neural networks

  2016cited by this paper
• Deep Learning without Poor Local Minima

  2016cited by this paper
• Symmetric Orthogonal Tensor Decomposition is Trivial

  2015influential reference
• Active Subspaces - Emerging Ideas for Dimension Reduction in Parameter Studies

  2015cited by this paper
• Finding a low-rank basis in a matrix subspace

  2015cited by this paper
• Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-1 Updates

  2014cited by this paper
• Breaking the Curse of Dimensionality with Convex Neural Networks

  2014influential reference
• Orthogonal Decomposition of Symmetric Tensors

  2014influential reference
• Finding a Sparse Vector in a Subspace: Linear Sparsity Using Alternating Directions

  2014cited by this paper
• Entropy and Sampling Numbers of Classes of Ridge Functions

  2013cited by this paper
• High-Performance OCR for Printed English and Fraktur Using LSTM Networks

  2013cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• Tensor Spaces and Numerical Tensor Calculus

  2012cited by this paper
• Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition

  2012cited by this paper
• Multi-column deep neural network for traffic sign classification

  2012cited by this paper
• I and J

  2012influential reference
• Topics in Random Matrix Theory

  2012influential reference
• Capturing Ridge Functions in High Dimensions from Point Queries

  2011cited by this paper
• Eigenvectors of tensors and algorithms for Waring decomposition

  2011cited by this paper
• Sums of random Hermitian matrices and an inequality by Rudelson

  2010cited by this paper
• Learning Functions of Few Arbitrary Linear Parameters in High Dimensions

  2010influential reference
• User-Friendly Tail Bounds for Sums of Random Matrices

  2010cited by this paper
• Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions

  2009influential reference
• Most Tensor Problems Are NP-Hard

  2009cited by this paper
• Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

  2006influential reference
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• Greedy Layer-Wise Training of Deep Networks

  2006cited by this paper
• Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem

  2006cited by this paper
• Sampling from large matrices: An approach through geometric functional analysis

  2005cited by this paper
• Singularities of linear systems and the Waring problem

  2004cited by this paper
• Convex Optimization

  2004influential reference
• Ridgelets: estimating with ridge functions

  2003cited by this paper
• Interpolation by ridge polynomials and its application in neural networks

  2002cited by this paper
• Weakly defective varieties

  2001cited by this paper
• Strong converse for identification via quantum channels

  2000cited by this paper
• Approximation by ridge functions and neural networks

  1999cited by this paper
• Identifying Linear Combinations of Ridge Functions

  1999cited by this paper
• Approximating by Ridge Functions

  1997influential reference
• Reconstructing a neural net from its output

  1994cited by this paper
• Linear Matrix Inequalities in Systems and Control Theory

  1994influential reference
• Ridge Functions, Sigmoidal Functions and Neural Networks

  1993cited by this paper
• On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma

  1992influential reference
• Original Contribution: Training a 3-node neural network is NP-complete

  1992cited by this paper
• Perturbation theory for the singular value decomposition

  1990influential reference
• Neural network design and the complexity of learning

  1990cited by this paper
• Projection-Based Approximation and a Duality with Kernel Methods

  1989cited by this paper
• Tensor Rank is NP-Complete

  1989cited by this paper
• What is projection pursuit

  1987cited by this paper
• Estimation of the Mean of a Multivariate Normal Distribution

  1981cited by this paper
• Optimal reconstruction of a function from its projections

  1975cited by this paper
• Perturbation bounds in connection with singular value decomposition

  1972cited by this paper

• Identifiability of Deep Polynomial Neural Networks

  2025cites this paper
• Efficient identification of wide shallow neural networks with biases

  2025cites this paper
• Low-Rank Tensor Decompositions for the Theory of Neural Networks

  2025cites this paper
• Finite Samples for Shallow Neural Networks

  2025cites this paper
• On best approximation by multivariate ridge functions with applications to generalized translation networks

  2024influential citation
• Expand-and-Cluster: Parameter Recovery of Neural Networks

  2023cites this paper
• Expand-and-Cluster: Exact Parameter Recovery of Neural Networks

  2023cites this paper
• Finite Sample Identification of Wide Shallow Neural Networks with Biases

  2022influential citation
• Efficient Identification of Butterfly Sparse Matrix Factorizations

  2021cites this paper
• Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples

  2021influential citation
• Going Beyond Linear RL: Sample Efficient Neural Function Approximation

  2021cites this paper
• Landscape analysis of an improved power method for tensor decomposition

  2021cites this paper
• Affine Symmetries and Neural Network Identifiability

  2020cites this paper
• Affine symmetries and neural network identifiability

  2020cites this paper
• Estimating multi-index models with response-conditional least squares

  2020cites this paper
• Robust and Resource-Efficient Identification of Two Hidden Layer Neural Networks

  2019cites this paper
• Algorithms and Complexity for Continuous Problems (Dagstuhl Seminar 19341)

  2019cites this paper
• Subspace power method for symmetric tensor decomposition and generalized PCA

  2019cites this paper