A theory of capacity and sparse neural encoding
From MaRDI portal
Publication:6079092
DOI10.1016/j.neunet.2021.05.005zbMath1521.68109arXiv2102.10148MaRDI QIDQ6079092
Publication date: 28 September 2023
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.10148
Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)
Related Items
Tractability from overparametrization: the example of the negative perceptron, What intraclass covariance structures can symmetric Bernoulli random variables have?, Lah distribution: Stirling numbers, records on compositions, and convex hulls of high-dimensional random walks
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A mathematical introduction to compressive sensing
- Asymptotic shape of a random polytope in a convex body
- Random projections of regular simplices
- Gaussian polytopes: a cumulant-based approach
- Random spaces generated by vertices of the cube
- Support-vector networks
- Random projections of regular polytopes
- The capacity of feedforward neural networks
- Dimension reduction by random hyperplane tessellations
- Cones generated by random points on half-spheres and convex hulls of Poisson point processes
- Universality in polytope phase transitions and message passing algorithms
- Central limit theorems for Gaussian polytopes
- Counting the faces of randomly-projected hypercubes and orthants, with applications
- Banach-Mazur distances and projections on random subgaussian polytopes
- One-bit compressed sensing with non-Gaussian measurements
- Smallest singular value of random matrices and geometry of random polytopes
- The geometry of random \(\{-1,1\}\)-polytopes
- The Generalized Lasso With Non-Linear Observations
- Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
- Counting faces of randomly projected polytopes when the projection radically lowers dimension
- The horseshoe estimator for sparse signals
- Linear Inversion of Band-Limited Reflection Seismograms
- EXTREMAL PROPERTIES OF ORTHOGONAL PARALLELEPIPEDS AND THEIR APPLICATIONS TO THE GEOMETRY OF BANACH SPACES
- Bayesian Variable Selection in Linear Regression
- 10.1162/15324430152748236
- Probability
- Expected intrinsic volumes and facet numbers of random beta‐polytopes
- High-Dimensional Probability
- Polynomial Threshold Functions, Hyperplane Arrangements, and Random Tensors
- Living on the edge: phase transitions in convex programs with random data
- Asymptotic Geometric Analysis, Part I
- Random Polytopes
- Neural networks and physical systems with emergent collective computational abilities.
- Gaussian polytopes: variances and limit theorems
- Deep Learning in Science
- Compressed sensing