Cover Image

On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Yeachan, Park, Sejun, Hwang, Geonho
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Expressive Power of Floating-Point Transformers
by: Park, Sejun, et al.
Published: (2026)

Expressive Power of ReLU and Step Networks under Floating-Point Operations
by: Park, Yeachan, et al.
Published: (2024)

Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
by: Park, Yeachan, et al.
Published: (2026)

Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
by: Park, Sejun, et al.
Published: (2026)

Floating-Point Neural Networks Are Provably Robust Universal Approximators
by: Hwang, Geonho, et al.
Published: (2025)

Minimum width for universal approximation using squashable activation functions
by: Shin, Jonghyun, et al.
Published: (2025)

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

Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
by: Hwang, Hyeonbin, et al.
Published: (2026)

Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation
by: Park, Yeachan, et al.
Published: (2024)

A Kernel Perspective on Distillation-based Collaborative Learning
by: Park, Sejun, et al.
Published: (2024)

Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
by: Hong, Kihun, et al.
Published: (2025)

IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs
by: Park, Sejun, et al.
Published: (2024)

Minimum width for universal approximation using ReLU networks on compact domain
by: Kim, Namjun, et al.
Published: (2023)

On the Expressive Power of Graph Neural Networks
by: Nalwade, Ashwin, et al.
Published: (2024)

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
by: Park, Hyuntae, et al.
Published: (2025)

On the Expressive Power of Geometric Graph Neural Networks
by: Joshi, Chaitanya K., et al.
Published: (2023)

On the Expressive Power of Subgraph Graph Neural Networks for Graphs with Bounded Cycles
by: Chen, Ziang, et al.
Published: (2025)

The Expressive Power of Graph Neural Networks: A Survey
by: Zhang, Bingxu, et al.
Published: (2023)

On Expressivity of Height in Neural Networks
by: Fan, Feng-Lei, et al.
Published: (2023)

A Theoretical Study of Neural Network Expressive Power via Manifold Topology
by: Yao, Jiachen, et al.
Published: (2024)

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
by: Wang, Zhe, et al.
Published: (2024)

Neural Shortest Path for Surface Reconstruction from Point Clouds
by: Park, Yesom, et al.
Published: (2025)

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
by: Chen, Ziang, et al.
Published: (2024)

Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
by: Hwang, Seohwa, et al.
Published: (2026)

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks
by: Chen, Jiawen, et al.
Published: (2026)

Unleashing the Expressive Power of Pulse-Based Quantum Neural Networks
by: Tao, Han-Xiao, et al.
Published: (2024)

Fixed-Point Neural Optimal Transport without Implicit Differentiation
by: Park, Yesom, et al.
Published: (2026)

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
by: Kim, Kwonyoung, et al.
Published: (2022)

Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction
by: Lu, Kangkang, et al.
Published: (2024)

Tropical Expressivity of Neural Networks
by: Lezeau, Paul, et al.
Published: (2024)

Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning
by: Chen, Shiyu, et al.
Published: (2025)

FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks
by: Kim, Jaemin, et al.
Published: (2025)

MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization
by: Kim, Daeun, et al.
Published: (2025)

Expressivity of deterministic quantum computation with one qubit
by: Kim, Yujin, et al.
Published: (2024)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
by: Dayan, Adir, et al.
Published: (2026)

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
by: Choi, Kanghyun, et al.
Published: (2025)

Arithmetic-Intensity-Aware Quantization
by: Singh, Taig, et al.
Published: (2025)

MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction
by: Park, Jun-Hyung, et al.
Published: (2024)

On the Expressive Power of Spectral Invariant Graph Neural Networks
by: Zhang, Bohang, et al.
Published: (2024)

Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
by: Lee, Hyunwoo, et al.
Published: (2024)