No article text was recorded for this version.
function-preserving network expansion
Version 1 of 122 papers30 conceptsfrozen 2026-10-04
Papers in this version
- Blog: $\mu$pscaling small models: Principled warm starts and hyperparameter transfer
- Blog: When and How to Grow? On Efficient Pre-training via Model Growth
- Blog: Net2Net: Accelerating Learning via Knowledge Transfer
- Blog: $μ$pscaling small models: Principled warm starts and hyperparameter transfer
- Blog: Data Efficient Neural Scaling Law via Model Reusing
- Blog: FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing
- Blog: On the Transformer Growth for Progressive BERT Training
- Blog: Embedding Principle of Homogeneous Neural Network for Classification Problem
- Blog: FedTrans: Efficient Federated Learning via Multi-Model Transformation
- Blog: Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations
- Blog: bert2BERT: Towards Reusable Pretrained Language Models
- Blog: Staged Training for Transformer Language Models
- Blog: Embedding Principle of Loss Landscape of Deep Neural Networks
- Blog: Estimation efficace des incertitudes avec Packed-Ensembles
- Blog: Net2Net: Accelerating Learning via Knowledge Transfer Tianqi Chen
- Blog: MotherNets: Rapid Deep Ensemble Learning
- Blog: MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters
- Blog: Efficient Architecture Search by Network Transformation
- Blog: Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
- Blog: Modularized Morphing of Neural Networks
- Blog: Expand Neurons, Not Parameters
- Blog: Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_function_preserving_network_expansion_8167cadf,
title = {function-preserving network expansion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/function-preserving-network-expansion/rdr_8167cadf4e2a415d8c816b449674bfb9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_function_preserving_network_expansion_8167cadf_v1,
title = {function-preserving network expansion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/function-preserving-network-expansion/rdr_8167cadf4e2a415d8c816b449674bfb9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}