Cover Image

Depth-Aware Initialization for Stable and Efficient Neural Network Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Pandey, Vijay
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

IDInit: A Universal and Stable Initialization Method for Neural Network Training
by: Pan, Yu, et al.
Published: (2025)

A Stable Whitening Optimizer for Efficient Neural Network Training
by: Frans, Kevin, et al.
Published: (2025)

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization
by: Jakub, Cameron, et al.
Published: (2023)

Deep Fusion: Efficient Network Training via Pre-trained Initializations
by: Mazzawi, Hanna, et al.
Published: (2023)

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
by: Kwok, Devin, et al.
Published: (2025)

A Training Framework for Optimal and Stable Training of Polynomial Neural Networks
by: Hossain, Forsad Al, et al.
Published: (2025)

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
by: Vessio, Gennaro
Published: (2025)

Sparsity-Aware Communication for Distributed Graph Neural Network Training
by: Mukhodopadhyay, Ujjaini, et al.
Published: (2025)

Effects of Initialization Biases on Deep Neural Network Training Dynamics
by: Pellegrino, Nicholas, et al.
Published: (2025)

UnifiedNN: Efficient Neural Network Training on the Cloud
by: Taki, Sifat Ut, et al.
Published: (2024)

Efficient Training of Probabilistic Neural Networks for Survival Analysis
by: Lillelund, Christian Marius, et al.
Published: (2024)

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
by: Bordelon, Blake, et al.
Published: (2025)

Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery
by: Guenter, Valentin Frank Ingmar, et al.
Published: (2024)

Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks
by: Kogler, Constantin, et al.
Published: (2026)

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

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
by: Revin, Ilia, et al.
Published: (2025)

Dynamic Rank Adjustment for Accurate and Efficient Neural Network Training
by: Shin, Hyuntak, et al.
Published: (2025)

A Depth-Aware Comparative Study of Euclidean and Hyperbolic Graph Neural Networks on Bitcoin Transaction Systems
by: Ghimire, Ankit, et al.
Published: (2026)

Optimal Depth of Neural Networks
by: Qi, Qian
Published: (2025)

Deep Neural Network Initialization with Sparsity Inducing Activations
by: Price, Ilan, et al.
Published: (2024)

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

Improved Depth Estimation of Bayesian Neural Networks
by: van Erp, Bart, et al.
Published: (2024)

Sharpness Aware Surrogate Training for Spiking Neural Networks
by: Nicholson, Maximilian
Published: (2026)

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)

Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
by: Gal, Eshed, et al.
Published: (2025)

CPT: Efficient Deep Neural Network Training via Cyclic Precision
by: Fu, Yonggan, et al.
Published: (2021)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
by: Muthuraman, Mannmohan
Published: (2025)

CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
by: Akhtar, Mushir, et al.
Published: (2026)

Deconstructing the Goldilocks Zone of Neural Network Initialization
by: Vysogorets, Artem, et al.
Published: (2024)

Union Subgraph Neural Networks
by: Xu, Jiaxing, et al.
Published: (2023)

Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks
by: Kelesis, Dimitrios, et al.
Published: (2024)

Initialization-enhanced Physics-Informed Neural Network with Domain Decomposition (IDPINN)
by: Si, Chenhao, et al.
Published: (2024)

On the Dataless Training of Neural Networks
by: Velasquez, Alvaro, et al.
Published: (2025)

StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths
by: Chen, Tianyi, et al.
Published: (2026)

Depth Separation in Norm-Bounded Infinite-Width Neural Networks
by: Parkinson, Suzanna, et al.
Published: (2024)

Depth Separations in Neural Networks: Separating the Dimension from the Accuracy
by: Safran, Itay, et al.
Published: (2024)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
by: Huang, Kezhao, et al.
Published: (2023)

Stable Port-Hamiltonian Neural Networks
by: Roth, Fabian J., et al.
Published: (2025)

Efficient, Accurate and Stable Gradients for Neural ODEs
by: McCallum, Sam, et al.
Published: (2024)