No article text was recorded for this version.
approximation efficiency
Version 1 of 1320 papers488 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Universal Approximation with Deep Narrow Networks
- Blog: Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
- Blog: Achieve the Minimum Width of Neural Networks for Universal Approximation
- Blog: Minimum Width for Universal Approximation using Squashable Activation Functions
- Blog: Minimum Width for Universal Approximation
- Blog: Minimum width for universal approximation using squashable activation functions
- Blog: Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations
- Blog: Approximating Continuous Functions by ReLU Nets of Minimal Width
- Blog: Deep Narrow Boltzmann Machines are Universal Approximators
- Blog: Minimum width for universal approximation using ReLU networks on compact domain
- Blog: Minimum Width for Deep, Narrow MLP: A Diffeomorphism and the Whitney Embedding Theorem Approach
- Blog: How Many Neurons Does it Take to Approximate the Maximum?
- Blog: Minimum width for universal approximation using ReLU networks on compact domain
- Blog: Optimal Approximation with Sparsely Connected Deep Neural Networks
- Blog: On the Universal Approximation Property of Deep Fully Convolutional Neural Networks
- Blog: Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units
- Blog: The Expressive Power of Neural Networks: A View from the Width
- Blog: Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
- Blog: Minimal Width for Universal Property of Deep RNN
- Blog: Minimal Width for Universal Property of Deep RNN
- Blog: Width is Less Important than Depth in ReLU Neural Networks
- Blog: Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
- Blog: ResNet with one-neuron hidden layers is a Universal Approximator
- Blog: Universal Approximation of Functions on Sets
- Blog: Universal approximation with complex-valued deep narrow neural networks
- Blog: Vanilla feedforward neural networks as a discretization of dynamic systems
- Blog: ResNet with one-neuron hidden layers is a Universal Approximator
- Blog: Characterizing ResNet's Universal Approximation Capability
- Blog: Universal Approximation by a Slim Network with Sparse Shortcut Connections
- Blog: Why Deep Neural Networks for Function Approximation
- Blog: Universal approximation power of deep residual neural networks via nonlinear control theory
- Blog: Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
- Blog: Some Estimates of Necessary Number of Connections and Hidden Units for Feed-Forward Networks
- Blog: A Minimal Control Family of Dynamical Syetem for Universal Approximation
- Blog: Approximation theory for 1-Lipschitz ResNets
- Blog: Expressivity of Deep Neural Networks
- Blog: Universal Approximation Power of Deep Neural Networks via Nonlinear Control Theory
- Blog: Restricted Boltzmann Machines: Introduction and Review
- Blog: ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate
- Blog: On a Sparse Shortcut Topology of Artificial Neural Networks
- Blog: Width is Less Important than Depth in ReLU Neural Networks
- Blog: On the Approximation Power of Two-Layer Networks of Random ReLUs
- Blog: The Expressive Power of Neural Networks: A View from the Width
- Blog: Generalizablity of Memorization Neural Network
- Blog: Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
- Blog: Topological Expressivity of ReLU Neural Networks
- Blog: Size and depth of monotone neural networks: interpolation and approximation
- Blog: New advances in universal approximation with neural networks of minimal width
- Blog: Sumformer: Universal Approximation for Efficient Transformers
- Blog: Depth Separations in Neural Networks: Separating the Dimension from the Accuracy
- Blog: How Neural Nets Work
- Blog: Towards Lower Bounds on the Depth of ReLU Neural Networks
- Blog: On the Approximation Power of Two-Layer Networks of Random ReLUs
- Blog: Lower bounds for artificial neural network approximations: A proof that shallow neural networks fail to overcome the curse of dimensionality
- Blog: Deep, Skinny Neural Networks are not Universal Approximators
- Blog: A Universal Uniform Approximation Theorem for Neural Networks
- Blog: Approximation theory for 1-Lipschitz ResNets
- Blog: Approximation and non-parametric estimation of ResNet-type convolutional neural networks
- Blog: Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem
- Blog: Mathematical Aspects of Neural Networks
Showing 60 of 320 papers.
History & citation
Current · Permanent link
- The Representational Power and Efficiency of Depth merged into this direction (56% overlap)
- Topological Limits on the Minimum Width of Deep Networks merged into this direction (54% overlap)
- Depth Separation for High Frequency and Radial Functions merged into this direction (50% overlap)
- Minimum Width Thresholds for Deep Neural Networks merged into this direction (92% overlap)
- Universal Approximation via Scalar Encoding merged into this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_approximation_efficiency_8270c0a3,
title = {approximation efficiency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/approximation-efficiency/rdr_8270c0a341d04f9789c190196fbb76a0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_approximation_efficiency_8270c0a3_v1,
title = {approximation efficiency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/approximation-efficiency/rdr_8270c0a341d04f9789c190196fbb76a0/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}