The Effective Depth Paradox: Topology and Trainability in Deep CNNs

Manfred Fischer () and Joshua Pitts

No 2, Working Papers in Regional Science from WU Vienna University of Economics and Business

Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topologies and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 using a unified experimental protocol. We revisit and formalize the distinction between nominal depth (Dnom), the physical count of weight bearing layers, and effective depth (Deff ), an operational metric that quantifies the expected length of forward information paths. The effective-depth construction builds directly on the ensemble interpretation of residual networks introduced by Veit et al. 2016. Our contribution is to (i) extend this pathaveraging logic into closed-form, pre-training proxies that span sequential, residual, and multi-branch topologies alike, (ii) validate a computationally cheap structural proxy against a gradient-weighted variant computed from observed backpropagation signal, and (iii) test the resulting "Effective Depth Paradox" — the empirical pattern whereby nominal depth alone is a poor predictor of trainability and accuracy — against results from eight representative models (VGG-11/13/16/19, ResNet-18/34/50, GoogLeNet). In our protocol, plain VGG-style stacks show early saturation in accuracy as Dnom grows, while ResNet and GoogLeNet continue to benefit from additional depth by keeping Deff low relative to Dnom. A pooled correlation analysis shows that both Dnom and Deff are strongly associated with precision (r = 0.94 and r = 0.93, respectively); given the small family-clustered sample, this analysis alone cannot cleanly separate the two metrics, and we treat the accompanying evidence of gradient-norm and gradient-weighted validation as complementary mechanistic support rather than as decisive statistical proof. All claims in this paper are scoped to CIFAR-10-scale training of the three architecture families studied; we explicitly do not claim validation at ImageNet scale or generalization to modern architectures such as EfficientNet, ConvNeXt, or Vision Transformers, which we identify as necessary future work.

Keywords: CNNs; Effective Depth (Deff ); Nominal Depth (Dnom); Gradient Flow Stability; Residual Connections; Multi-Branching Modules; Architectural Scaling Laws (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://research.wu.ac.at/en/publications/39474f89-6ee9-4bcd-a3db-c49fdf2b0cd1 original version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wiw:wus046:81798935

Access Statistics for this paper

More papers in Working Papers in Regional Science from WU Vienna University of Economics and Business Welthandelsplatz 1, 1020 Vienna, Austria.
Bibliographic data for series maintained by WU Library ().