Imagen de Portada

Dispelling the Curse of Singularities in Neural Network Optimizations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Hengjie, Chen, Mengyi, Yang, Yifeng, Dong, Fang, Huang, Ruijun, Chen, Anrui, Zhou, Jixian, Dong, Mingzhi, Wang, Yujiang, Li, Dongsheng, Fang, Wenyi, Lin, Yuanyi, Wu, Fan, Shang, Li
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
por: Cao, Hengjie, et al.
Publicado: (2026)

Metis: Training LLMs with FP4 Quantization
por: Cao, Hengjie, et al.
Publicado: (2025)

Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy
por: Huang, Zhendong, et al.
Publicado: (2026)

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
por: Chen, Anrui, et al.
Publicado: (2026)

SD-MoE: Spectral Decomposition for Effective Expert Specialization
por: Huang, Ruijun, et al.
Publicado: (2026)

On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
por: Li, Zhong, et al.
Publicado: (2020)

Curse of Dimensionality in Neural Network Optimization
por: Na, Sanghoon, et al.
Publicado: (2025)

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
por: Wang, Chenyu, et al.
Publicado: (2024)

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
por: Shi, Yubin, et al.
Publicado: (2024)

Postbiotics: Enhancing human health with a novel concept
por: Mingzhi Da, et al.
Publicado: (2024)

Medical records condensation: a roadmap towards healthcare data democratisation
por: Wang, Yujiang, et al.
Publicado: (2023)

Smart Predict-then-Optimize Method with Dependent Data: Risk Bounds and Calibration of Autoregression
por: Liu, Jixian, et al.
Publicado: (2024)

LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
por: Budzinskiy, Stanislav, et al.
Publicado: (2026)

Pregnancy Outcome in Vascular Ehlers–Danlos Syndrome
por: Fang Chen, et al.
Publicado: (2025)

Inclusive Learning Analytics with Embedded Data Comics: A Conceptual Framework for Public Understanding of AI Ethics
por: Wei, Mengyi, et al.
Publicado: (2026)

Dispelling Bottled Water Myths
por: Naeem Qureshi, et al.
Publicado: (2025)

Dispelling and returning: The deconstruction and remodelling of China's pre‐reorganisation system
por: Yuxia Song, et al.
Publicado: (2025)

Inference of Parameters for Back-shifted Fermi Gas Model using Feedback Neural Network
por: Du, Peng-Xiang, et al.
Publicado: (2024)

Learning Macroscopic Dynamics from Partial Microscopic Observations
por: Chen, Mengyi, et al.
Publicado: (2024)

Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG
por: Fang, Chenhao, et al.
Publicado: (2024)

Optimal error analysis of an interior penalty virtual element method for fourth-order singular perturbation problems
por: Feng, Fang, et al.
Publicado: (2025)

Compositional Function Networks: A High-Performance Alternative to Deep Neural Networks with Built-in Interpretability
por: Li, Fang
Publicado: (2025)

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

Myths about Sustainable Consumption: Dispelled
Publicado: (2026)

Dispelling Myths About Water Services
por: Richard G. Little
Publicado: (2025)

Biosensing materials for monoclonal antibody detection: An overview
por: Yuxin Zhang, et al.
Publicado: (2024)

Machine Learning-Assisted Optimization of Modular Neutron Shielding Based on Monte Carlo Simulations
por: Chen, Li-Fang
Publicado: (2025)

Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
por: Hu, Zheyuan, et al.
Publicado: (2023)

Singular sets in noncollapsed Ricci flow limit spaces
por: Fang, Hanbing, et al.
Publicado: (2025)

Meerkat: A Distributed Reactive Programming Language with Live Updates
por: Zhong, Heng, et al.
Publicado: (2024)

Dispelling the magic of artificial intelligence in medical education
por: Casey N. McQuade, et al.
Publicado: (2024)

Ciphertext-Policy ABE for $\mathsf{NC}^1$ Circuits with Constant-Size Ciphertexts from Succinct LWE
por: Liu, Jiaqi, et al.
Publicado: (2026)

Parallel Collaborative ADMM Privacy Computing and Adaptive GPU Acceleration for Distributed Edge Networks
por: Xia, Mengchun, et al.
Publicado: (2026)

On Galois theory of cluster algebras: general and that from Riemann surfaces
por: Dong, Jinlei, et al.
Publicado: (2024)

EMIF: Evidence-aware Multi-source Information Fusion Network for Explainable Fake News Detection
por: Dong, Qingxing, et al.
Publicado: (2024)

Electromagnetohydrodynamic (EMHD) flow of Jeffrey fluid through a rough circular microchannel with surface charge–dependent slip
por: Dongsheng Li, et al.
Publicado: (2024)

Integer Binary-Range Alignment Neuron for Spiking Neural Networks
por: Ye, Binghao, et al.
Publicado: (2025)

The Ingroup–Outgroup Effect of Implicit Social Hierarchy Stereotypes
por: Yujiang Zhou, et al.
Publicado: (2025)

ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
por: Zhu, Mingzhi, et al.
Publicado: (2025)

Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
por: Shang, Sifeng, et al.
Publicado: (2025)