Image de couverture de livre

When do complex-valued neural networks help? A study of representation, geometry, and optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Kumar, Ashutosh
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

$Δ$-PINNs: physics-informed neural networks on complex geometries
par: Costabal, Francisco Sahli, et autres
Publié: (2022)

How does training shape the Riemannian geometry of neural network representations?
par: Zavatone-Veth, Jacob A., et autres
Publié: (2023)

When do neural ordinary differential equations generalize on complex networks?
par: Laber, Moritz, et autres
Publié: (2026)

Universal approximation with complex-valued deep narrow neural networks
par: Geuchen, Paul, et autres
Publié: (2023)

Task complexity shapes internal representations and robustness in neural networks
par: Jankowski, Robert, et autres
Publié: (2025)

Category learning in deep neural networks: Information content and geometry of internal representations
par: Bonnasse-Gahot, Laurent, et autres
Publié: (2025)

Orders-of-coupling representation with a single neural network with optimal neuron activation functions and without nonlinear parameter optimization
par: Manzhos, Sergei, et autres
Publié: (2023)

Why are hyperbolic neural networks effective? A study on hierarchical representation capability
par: Tan, Shicheng, et autres
Publié: (2024)

Toric geometry of ReLU neural networks
par: Fu, Yaoying
Publié: (2025)

Scalable neural network-based blackbox optimization
par: Koratikere, Pavankumar, et autres
Publié: (2025)

From superposition to sparse codes: interpretable representations in neural networks
par: Klindt, David, et autres
Publié: (2025)

Shape-morphing programming of soft materials on complex geometries via neural operator
par: Chen, Lu, et autres
Publié: (2026)

Interpretable statistical representations of neural population dynamics and geometry
par: Gosztolai, Adam, et autres
Publié: (2023)

The sampling complexity of learning invertible residual neural networks
par: Li, Yuanyuan, et autres
Publié: (2024)

Contrast transfer functions help quantify neural network out-of-distribution generalization in HRTEM
par: DaCosta, Luis Rangel, et autres
Publié: (2025)

When do spectral gradient updates help in deep learning?
par: Davis, Damek, et autres
Publié: (2025)

Accuracy estimation of neural networks by extreme value theory
par: Junike, Gero, et autres
Publié: (2025)

Early learning of the optimal constant solution in neural networks and humans
par: Rubruck, Jirko, et autres
Publié: (2024)

Addressing divergent representations from causal interventions on neural networks
par: Grant, Satchel, et autres
Publié: (2025)

Resolution invariant deep operator network for PDEs with complex geometries
par: Huang, Jianguo, et autres
Publié: (2024)

A constrained optimization approach to improve robustness of neural networks
par: Zhao, Shudian, et autres
Publié: (2024)

BayesFlow: Learning complex stochastic models with invertible neural networks
par: Radev, Stefan T., et autres
Publié: (2020)

Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks
par: Truong, Nhut, et autres
Publié: (2025)

Human alignment of neural network representations
par: Muttenthaler, Lukas, et autres
Publié: (2022)

Computing high-dimensional optimal transport by flow neural networks
par: Xu, Chen, et autres
Publié: (2023)

Differentiable neural network representation of multi-well, locally-convex potentials
par: Jones, Reese E., et autres
Publié: (2025)

Connecting the geometry and dynamics of many-body complex systems with message passing neural operators
par: Gabriel, Nicholas A., et autres
Publié: (2025)

On the geometry and topology of representations: the manifolds of modular addition
par: Moisescu-Pareja, Gabriela, et autres
Publié: (2025)

Gradient-based inference of abstract task representations for generalization in neural networks
par: Hummos, Ali, et autres
Publié: (2024)

Formulations and scalability of neural network surrogates in nonlinear optimization problems
par: Parker, Robert B., et autres
Publié: (2024)

Adaptive multiple optimal learning factors for neural network training
par: Challagundla, Jeshwanth
Publié: (2024)

Simmering: Sufficient is better than optimal for training neural networks
par: Babayan, Irina, et autres
Publié: (2024)

An analysis of optimization problems involving ReLU neural networks
par: Plate, Christoph, et autres
Publié: (2025)

Flow reconstruction in time-varying geometries using graph neural networks
par: Danciu, Bogdan A., et autres
Publié: (2024)

When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning
par: Voelcker, Claas, et autres
Publié: (2024)

Minimax optimality of deep neural networks on dependent data via PAC-Bayes bounds
par: Alquier, Pierre, et autres
Publié: (2024)

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response
par: Patel, Ravi, et autres
Publié: (2024)

Advanced atom-level representations for protein flexibility prediction utilizing graph neural networks
par: Sarparast, Sina, et autres
Publié: (2024)

Stretched and measured neural predictions of complex network dynamics
par: Vasiliauskaite, Vaiva, et autres
Publié: (2023)

Biology-informed neural networks learn nonlinear representations from omics data to improve genomic prediction and interpretability
par: Kontolati, Katiana, et autres
Publié: (2025)