A Compact Network Learning Model for Distribution Regression
This addresses a bottleneck in distribution regression for machine learning applications, offering a more efficient solution.
The paper tackles the problem of regression on function spaces by proposing a compact network representation that encodes entire functions in single nodes, achieving higher prediction accuracies with fewer parameters than traditional neural networks.
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an entire function in a single network node. To that end, we design a compact network representation that encodes and propagates functions in single nodes for the distribution regression task. Our proposed Distribution Regression Network (DRN) achieves higher prediction accuracies while being much more compact and uses fewer parameters than traditional neural networks.