On Neural Network Pruning’s Effect on Generalization
Practitioners frequently observe that pruning improves model generalization. A longstanding hypothesis attributes such improvement to model size reduction. However, recent studies on over-parameterization characterize a new model size regime, in which larger models achieve better generalization. A c...
Main Author: | Jin, Tian |
---|---|
Other Authors: | Carbin, Michael |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/147496 |
Similar Items
-
Transformer Pruning Relation and General Neural Network Augmentation
by: Lim, Yong Hui
Published: (2022) -
Neural network pruning for face anti-spoofing
by: Zhang, Yinan
Published: (2022) -
Feature selection for classification applications in neural network pruning
by: Gong, Rui
Published: (2024) -
Stock selection using General Growing and Pruning Radial Basis Function (GGAP-RBF) neural network
by: Ng, Wee Ding.
Published: (2010) -
Resource efficient neural networks through Hessian based pruning
by: Chong, Jack Huai Jie
Published: (2023)