English

Dataless Model Selection with the Deep Frame Potential

Machine Learning 2020-04-01 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Choosing a deep neural network architecture is a fundamental problem in applications that require balancing performance and parameter efficiency. Standard approaches rely on ad-hoc engineering or computationally expensive validation on a specific dataset. We instead attempt to quantify networks by their intrinsic capacity for unique and robust representations, enabling efficient architecture comparisons without requiring any data. Building upon theoretical connections between deep learning and sparse approximation, we propose the deep frame potential: a measure of coherence that is approximately related to representation stability but has minimizers that depend only on network structure. This provides a framework for jointly quantifying the contributions of architectural hyper-parameters such as depth, width, and skip connections. We validate its use as a criterion for model selection and demonstrate correlation with generalization error on a variety of common residual and densely connected network architectures.

Keywords

Cite

@article{arxiv.2003.13866,
  title  = {Dataless Model Selection with the Deep Frame Potential},
  author = {Calvin Murdock and Simon Lucey},
  journal= {arXiv preprint arXiv:2003.13866},
  year   = {2020}
}

Comments

Oral presentation at the Conference on Computer Vision and Pattern Recognition (CVPR), 2020

R2 v1 2026-06-23T14:32:58.747Z