Cover Image

IDInit: A Universal and Stable Initialization Method for Neural Network Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Yu, Wang, Chaozheng, Wu, Zekai, Wang, Qifan, Zhang, Min, Xu, Zenglin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
by: Zou, Mingxi, et al.
Published: (2026)

Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems
by: Guo, Ping, et al.
Published: (2021)

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making
by: Chen, Jiaxiang, et al.
Published: (2025)

Preparing Lessons for Progressive Training on Language Models
by: Pan, Yu, et al.
Published: (2024)

GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks
by: Li, Xuyan, et al.
Published: (2025)

CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling
by: Qu, Zekai, et al.
Published: (2025)

UMoE: Unifying Attention and FFN with Shared Experts
by: Yang, Yuanhang, et al.
Published: (2025)

Trustworthy Graph Neural Networks: Aspects, Methods and Trends
by: Zhang, He, et al.
Published: (2022)

Principal Components for Neural Network Initialization
by: Phan, Nhan, et al.
Published: (2025)

LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
by: Kim, Hyunjun
Published: (2026)

Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
by: Liu, Xin, et al.
Published: (2022)

Efficient Network Automatic Relevance Determination
by: Zhang, Hongwei, et al.
Published: (2025)

A General Method for Proving Networks Universal Approximation Property
by: Wang, Wei
Published: (2025)

Cumulative Distribution Function based General Temporal Point Processes
by: Wang, Maolin, et al.
Published: (2024)

Fast Training of Sinusoidal Neural Fields via Scaling Initialization
by: Yeom, Taesun, et al.
Published: (2024)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
by: Cho, Wonyong, et al.
Published: (2026)

Universal Prompt Tuning for Graph Neural Networks
by: Fang, Taoran, et al.
Published: (2022)

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation
by: Xu, Chenhui, et al.
Published: (2024)

HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
by: Min, Youngjae, et al.
Published: (2024)

Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training
by: Chaudhary, Jatin, et al.
Published: (2024)

Improving Line Search Methods for Large Scale Neural Network Training
by: Kenneweg, Philip, et al.
Published: (2024)

Native Fortran Implementation of TensorFlow-Trained Deep and Bayesian Neural Networks
by: Furlong, Aidan, et al.
Published: (2025)

Time Series Analysis for Education: Methods, Applications, and Future Directions
by: Mao, Shengzhong, et al.
Published: (2024)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
by: Cao, Yuan-dong, et al.
Published: (2026)

Dynamic Universal Approximation Theory: Foundations for Parallelism in Neural Networks
by: Wang, Wei, et al.
Published: (2024)

IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting
by: Wu, Beiliang, et al.
Published: (2025)

4-bit Shampoo for Memory-Efficient Network Training
by: Wang, Sike, et al.
Published: (2024)

A Survey on Graph Neural Networks for Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
by: Wang, Yucheng, et al.
Published: (2024)

Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training
by: Wang, Ting, et al.
Published: (2025)

ROOT: Robust Orthogonalized Optimizer for Neural Network Training
by: He, Wei, et al.
Published: (2025)

Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
by: Li, Zhe, et al.
Published: (2023)

DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
by: Zhang, Zeyu, et al.
Published: (2024)

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

Quantum Optimization for Training Quantum Neural Networks
by: Liao, Yidong, et al.
Published: (2021)

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
by: Downer, Jane, et al.
Published: (2024)

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook
by: Deng, Juncan, et al.
Published: (2024)

Unsupervised Identification and Replay-based Detection (UIRD) for New Category Anomaly Detection in ECG Signal
by: Shi, Zhangyue, et al.
Published: (2025)

Accelerating Storage-Based Training for Graph Neural Networks
by: Jang, Myung-Hwan, et al.
Published: (2026)

Neural Representation for Wireless Radiation Field Reconstruction: A 3D Gaussian Splatting Approach
by: Wen, Chaozheng, et al.
Published: (2024)

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
by: Zhang, Zeliang, et al.
Published: (2024)