Low-dimensional topology of deep neural networks
arXiv:2606.31856
2026
Architecture
2 ideas extracted · analyzed Aug 29, 2026
What the math gives to ML
The paper supplies a concrete geometric criterion for distinguishing architectures: whether their layer maps can change the linking number of two disjoint embedded data manifolds in a three-dimensional representation space. The most transferable result is not the invariant itself, but the constructive observation that discrete residual blocks can synthesize folds such as absolute value, while continuous invertible flows cannot change linking number. This suggests narrow bottleneck architectures with explicit non-injective fold primitives, and layerwise topology diagnostics or regularizers for tasks whose classes require folding and unlinking.
Ideas from this paper
Unverified
Re-invented
2026
Replace part of a narrow ReLU MLP or residual branch with an explicit coordinatewise fold that computes absolute value in one residual block. The fold introduces controlled non-injectivity without increasing representation width, potentially allowing width-constrained networks to represent multimodal or topologically folded decision boundaries that monotone feedforward layers represent inefficiently.
Useful7/10
Difficulty3/10
Novelty5/10
Unverified
2026
Use linking number as a diagnostic and optional regularizer for representations of paired closed data manifolds. The probe identifies layers that collapse or separate class geometry through collisions and folds, giving an architecture-selection signal beyond loss and Jacobian singular values.
Useful5/10
Difficulty7/10
Novelty8/10