Image de couverture de livre

Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Park, Yeachan, Hwang, Geonho, Lee, Wonyeol, Park, Sejun
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

Expressive Power of ReLU and Step Networks under Floating-Point Operations
par: Park, Yeachan, et autres
Publié: (2024)

On the Expressive Power of Floating-Point Transformers
par: Park, Sejun, et autres
Publié: (2026)

Floating-Point Neural Networks Are Provably Robust Universal Approximators
par: Hwang, Geonho, et autres
Publié: (2025)

On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic
par: Park, Yeachan, et autres
Publié: (2024)

Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
par: Park, Sejun, et autres
Publié: (2026)

Minimum width for universal approximation using squashable activation functions
par: Shin, Jonghyun, et autres
Publié: (2025)

Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networks
par: Park, Yeachan
Publié: (2024)

Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
par: Hwang, Hyeonbin, et autres
Publié: (2026)

A Kernel Perspective on Distillation-based Collaborative Learning
par: Park, Sejun, et autres
Publié: (2024)

Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
par: Hong, Kihun, et autres
Publié: (2025)

IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs
par: Park, Sejun, et autres
Publié: (2024)

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
par: Park, Hyuntae, et autres
Publié: (2025)

Minimum width for universal approximation using ReLU networks on compact domain
par: Kim, Namjun, et autres
Publié: (2023)

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
par: Wang, Zhe, et autres
Publié: (2024)

The Hidden Power of Pure 16-bit Floating-Point Neural Networks
par: Yun, Juyoung, et autres
Publié: (2023)

Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
par: Lee, Changwon, et autres
Publié: (2024)

Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation
par: Park, Yeachan, et autres
Publié: (2024)

On the Expressive Power of Graph Neural Networks
par: Nalwade, Ashwin, et autres
Publié: (2024)

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
par: Choi, Kanghyun, et autres
Publié: (2025)

On the Expressive Power of Geometric Graph Neural Networks
par: Joshi, Chaitanya K., et autres
Publié: (2023)

Floating-Point Neural Network Verification at the Software Level
par: Manino, Edoardo, et autres
Publié: (2025)

MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction
par: Park, Jun-Hyung, et autres
Publié: (2024)

On the Expressive Power of Subgraph Graph Neural Networks for Graphs with Bounded Cycles
par: Chen, Ziang, et autres
Publié: (2025)

Self-supervised Adversarial Purification for Graph Neural Networks
par: Lee, Woohyun, et autres
Publié: (2026)

The Expressive Power of Graph Neural Networks: A Survey
par: Zhang, Bingxu, et autres
Publié: (2023)

Temporal Graph Learning Recurrent Neural Network for Traffic Forecasting
par: Lee, Sanghyun, et autres
Publié: (2024)

Floating-Body Hydrodynamic Neural Networks
par: Zhang, Tianshuo, et autres
Publié: (2025)

On Expressivity of Height in Neural Networks
par: Fan, Feng-Lei, et autres
Publié: (2023)

A Theoretical Study of Neural Network Expressive Power via Manifold Topology
par: Yao, Jiachen, et autres
Publié: (2024)

Neural Shortest Path for Surface Reconstruction from Point Clouds
par: Park, Yesom, et autres
Publié: (2025)

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
par: Chen, Ziang, et autres
Publié: (2024)

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks
par: Chen, Jiawen, et autres
Publié: (2026)

Unleashing the Expressive Power of Pulse-Based Quantum Neural Networks
par: Tao, Han-Xiao, et autres
Publié: (2024)

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)
par: Nam, Yoonsoo, et autres
Publié: (2025)

Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction
par: Lu, Kangkang, et autres
Publié: (2024)

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
par: Yao, Jianzhu, et autres
Publié: (2025)

Tropical Expressivity of Neural Networks
par: Lezeau, Paul, et autres
Publié: (2024)

Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning
par: Chen, Shiyu, et autres
Publié: (2025)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
par: Dayan, Adir, et autres
Publié: (2026)

Expressivity of deterministic quantum computation with one qubit
par: Kim, Yujin, et autres
Publié: (2024)