# Deep Learning: Generalization Requires Deep Compositional Feature Space Design

arXiv: https://arxiv.org/abs/1706.01983 · HTML: https://mlsanity.com/paper/1706.01983/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2017.

## Built on by (most cited first, 1 of 1)

- [Table Detection in the Wild: A Novel Diverse Table Detection Dataset and Method](https://mlsanity.com/paper/2209.09207/) (2022)

## Abstract (arXiv)

Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to convolution and max pooling can be marginalized with the compositional design, improving generalization performance. Also, we will show that learning rate decay acts as an implicit regularizer in deep model training.