Copertina

DiBA: Diagonal and Binary Matrix Approximation for Neural Network Weight Compression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Ono, Nobutaka
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Low-Rank Matrix Approximation for Neural Network Compression
di: Cherukuri, Kalyan, et al.
Pubblicazione: (2025)

Fast Swap-Based Element Selection for Multiplication-Free Dimension Reduction
di: Ono, Nobutaka
Pubblicazione: (2026)

Neural Networks With Dense Weights Are Not Universal Approximators
di: Rauchwerger, Levi, et al.
Pubblicazione: (2026)

Fast and Slow Gradient Approximation for Binary Neural Network Optimization
di: Chen, Xinquan, et al.
Pubblicazione: (2024)

Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees
di: Eamaz, Arian, et al.
Pubblicazione: (2025)

Neural Weight Compression for Language Models
di: Ryu, Jegwang, et al.
Pubblicazione: (2025)

Trade-Offs of Diagonal Fisher Information Matrix Estimators
di: Soen, Alexander, et al.
Pubblicazione: (2024)

Clustering-Based Low-Rank Matrix Approximation for Medical Image Compression
di: Hamlomo, Sisipho, et al.
Pubblicazione: (2025)

Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks
di: Chen, Ying, et al.
Pubblicazione: (2026)

Approximating Matrix Functions with Deep Neural Networks and Transformers
di: Padmanabhan, Rahul, et al.
Pubblicazione: (2026)

An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
di: Dehghankar, Mohsen, et al.
Pubblicazione: (2024)

Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases
di: Wolfson, Daniel, et al.
Pubblicazione: (2026)

Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors
di: Gorbett, Matt, et al.
Pubblicazione: (2024)

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
di: Zollicoffer, Geigh, et al.
Pubblicazione: (2024)

Matrix Manifold Neural Networks++
di: Nguyen, Xuan Son, et al.
Pubblicazione: (2024)

DiSGMM: A Method for Time-varying Microscopic Weight Completion on Road Networks
di: Lin, Yan, et al.
Pubblicazione: (2026)

Concatenated Matrix SVD: Compression Bounds, Incremental Approximation, and Error-Constrained Clustering
di: Shamrai, Maksym
Pubblicazione: (2026)

Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution
di: Allen, Kenneth, et al.
Pubblicazione: (2023)

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
di: Balasubramanian, Krishnakumar, et al.
Pubblicazione: (2025)

Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
di: Suzuki, Shota, et al.
Pubblicazione: (2025)

Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation
di: Huang, Kevin Han, et al.
Pubblicazione: (2025)

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
di: Elsayed, Mohamed, et al.
Pubblicazione: (2024)

Diagonal Adaptive Non-local Observables on Quantum Neural Networks
di: Tseng, Huan-Hsin, et al.
Pubblicazione: (2026)

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
di: Meng, Qingyan, et al.
Pubblicazione: (2025)

Information Plane Analysis of Binary Neural Networks
di: Nothnagel, Maximilian, et al.
Pubblicazione: (2026)

Dynamic Sparse Training of Diagonally Sparse Networks
di: Tyagi, Abhishek, et al.
Pubblicazione: (2025)

Model Compression Method for S4 with Diagonal State Space Layers using Balanced Truncation
di: Ezoe, Haruka, et al.
Pubblicazione: (2024)

Neural Networks Trained by Weight Permutation are Universal Approximators
di: Cai, Yongqiang, et al.
Pubblicazione: (2024)

Enabling On-device Continual Learning with Binary Neural Networks
di: Vorabbi, Lorenzo, et al.
Pubblicazione: (2024)

Seeking Interpretability and Explainability in Binary Activated Neural Networks
di: Leblanc, Benjamin, et al.
Pubblicazione: (2022)

Self-Compressing Neural Networks
di: Cséfalvay, Szabolcs, et al.
Pubblicazione: (2023)

Neural Network Compression for Reinforcement Learning Tasks
di: Ivanov, Dmitry A., et al.
Pubblicazione: (2024)

Simultaneous Weight and Architecture Optimization for Neural Networks
di: Huang, Zitong, et al.
Pubblicazione: (2024)

On the Effectiveness of Random Weights in Graph Neural Networks
di: Bui, Thu, et al.
Pubblicazione: (2025)

Weight-Space Linear Recurrent Neural Networks
di: Nzoyem, Roussel Desmond, et al.
Pubblicazione: (2025)

Multigrade Neural Network Approximation
di: Zhang, Shijun, et al.
Pubblicazione: (2026)

Neural Network Training with Approximate Logarithmic Computations
di: Sanyal, Arnab, et al.
Pubblicazione: (2019)

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
di: Tian, Bowen, et al.
Pubblicazione: (2025)

Monomial Matrix Group Equivariant Neural Functional Networks
di: Tran, Viet-Hoang, et al.
Pubblicazione: (2024)

Hyperbolic Binary Neural Network
di: Chen, Jun, et al.
Pubblicazione: (2025)