conftrace_

weight initialization

50 papers

Explore in graph

Co-occurring keywords

neural network optimization (1293) neural network (6616) model compression (3302) deep neural network (1803) neural network training (309) activation function (133) transfer learning (5449) model initialization (32) convolutional neural network (4226) signal propagation (20)

Papers

Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin JMLR 2025
WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement AAAI 2025
ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints ICCV 2025
MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters WACV 2024
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity NIPS 2024
Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields WACV 2024
Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes EMNLP 2024
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation NIPS 2024
Unraveling the Gradient Descent Dynamics of Transformers NIPS 2024
If You Want to Be Robust, Be Wary of Initialization NIPS 2024
Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models IJCAI 2024
Can We Find Strong Lottery Tickets in Generative Models? AAAI 2023
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks AAAI 2023
On the Initialization of Graph Neural Networks ICML 2023
Mimetic Initialization of Self-Attention Layers ICML 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023
Principled Weight Initialisation for Input-Convex Neural Networks NIPS 2023
How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives ACL 2023
Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022
A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks ICML 2022
Towards Understanding the Condensation of Neural Networks at Initial Training NIPS 2022
Revisiting Weight Initialization of Deep Neural Networks ACML 2021
What’s Hidden in a One-layer Randomly Weighted Transformer? EMNLP 2021
Learned Initializations for Optimizing Coordinate-Based Neural Representations CVPR 2021