Pith. sign in

Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic properties of the model to determine whether it is learning appropriately. In this work, we suggest studying the training of neural networks with Algebraic Topology, specifically Persistent Homology (PH). Using simplicial complex representations of neural networks, we study the PH diagram distance evolution on the neural network learning process with different architectures and several datasets. Results show that the PH diagram distance between consecutive neural network states correlates with the validation accuracy, implying that the generalization error of a neural network could be intrinsically estimated without any holdout set.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

A Quotient Homology Theory of Representation in Neural Networks

cs.LG · 2025-02-03 · conditional · novelty 7.0

For ReLU networks, the homology of the output representation is isomorphic to the homology of the input manifold quotiented by the network's overlap decomposition, when polyhedron-manifold intersections are convex.

citing papers explorer

Showing 1 of 1 citing paper.

  • A Quotient Homology Theory of Representation in Neural Networks cs.LG · 2025-02-03 · conditional · none · ref 19 · internal anchor

    For ReLU networks, the homology of the output representation is isomorphic to the homology of the input manifold quotiented by the network's overlap decomposition, when polyhedron-manifold intersections are convex.