Published June 27, 2023
| Version v1
Conference paper
Open
Learning distinct features helps, provably
- 1. Faculty of Information Technology and Communication Sciences Tampere University, Finland
- 2. Faculty of Information Technology, University of Jyväskylä, Finland & Programme for Environmental Information, Finnish Environment Institute, Jyväskylä, Finland
- 3. Department of Electrical and Computer Engineering Aarhus University, Denmark
Description
We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average L2-distance between the hidden-layer features and theoretically investigate how learning non-redundant distinct features affects the performance of the network. To do so, we derive novel generalization bounds depending on feature diversity based on Rademacher complexity for such networks. Our analysis proves that more distinct features at the network’s units within the hidden layer lead to better generalization. We also show how to extend our results to deeper networks and different losses.
Notes
Files
ECMLPKDD_learning_distinct_features_helps.pdf
Files
(619.8 kB)
Name | Size | Download all |
---|---|---|
md5:84238afdfa4b2bcec51b6df382ad810b
|
619.8 kB | Preview Download |