Conjugation by a cut-off Jastrow factor improves the spectral Barron regularity of Coulombic eigenfunctions from s<1 to s<2.
hub
R, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans
8 Pith papers cite this work, alongside 2,849 external citations. Polarity classification is still indexing.
8
Pith papers citing it
2,849
external citations · OpenAlex
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A classical polynomial-time algorithm for optimized sampling of lottery tickets in neural networks removes the exponential dependence on data dimension from prior classical approaches.
Shallow neural networks with time-frequency localized activations achieve dimension-independent Sobolev approximation rates of order N^{-1/2} for functions in weighted modulation spaces.
QCPIKAN is a quantum-classical physics-informed KAN that claims exponential high-frequency error convergence and superior accuracy over prior QCPINNs on single-phase, transport, and two-phase seepage PDEs.
SDAMI detects interactions in high-dimensional data via an Effect Footprint principle and models them using sparsity, group lasso, and dedicated deep subnetworks for improved interpretability.
Applies optimal transport to bound OOD generalization error in Transformers via Lipschitz continuity and TC^0 circuit depth lower bounds for Dyck-k backtracking, supported by evaluations on 54 configurations.
Recurrent networks built from tunable expressive neurons reveal scaling laws with an optimal parameter split that shifts toward higher per-neuron complexity at larger scales.
citing papers explorer
-
Cut-off Jastrow Factors and Spectral Barron Regularity of Coulombic Electronic Wave Functions
Conjugation by a cut-off Jastrow factor improves the spectral Barron regularity of Coulombic eigenfunctions from s<1 to s<2.
-
Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
A classical polynomial-time algorithm for optimized sampling of lottery tickets in neural networks removes the exponential dependence on data dimension from prior classical approaches.
-
Time-Frequency Analysis for Neural Networks
Shallow neural networks with time-frequency localized activations achieve dimension-independent Sobolev approximation rates of order N^{-1/2} for functions in weighted modulation spaces.
-
Quantum-classical physics-informed Kolmogorov-Arnold networks for PDEs
QCPIKAN is a quantum-classical physics-informed KAN that claims exponential high-frequency error convergence and superior accuracy over prior QCPINNs on single-phase, transport, and two-phase seepage PDEs.
-
Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
SDAMI detects interactions in high-dimensional data via an Effect Footprint principle and models them using sparsity, group lasso, and dedicated deep subnetworks for improved interpretability.
-
A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
Applies optimal transport to bound OOD generalization error in Transformers via Lipschitz continuity and TC^0 circuit depth lower bounds for Dyck-k backtracking, supported by evaluations on 54 configurations.
-
Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
Recurrent networks built from tunable expressive neurons reveal scaling laws with an optimal parameter split that shifts toward higher per-neuron complexity at larger scales.
- Spectral Barron spaces of vector-valued functions on compact groups