{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreieoxlkv7axhrkkjnyo4zq4x47srv67rvadkgmvqqjtoulbtwwcce4",
"uri": "at://did:plc:4rgrdigiftglskeax4wvmsev/app.bsky.feed.post/3mfsu2kiqs6i2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiflo6xt7is6b2iafwghkjahlgggocme5jwjsbeuqqwcywuvjhmszm"
},
"mimeType": "image/png",
"size": 24783
},
"path": "/abs/2602.22873v1",
"publishedAt": "2026-02-27T01:00:00.000Z",
"site": "https://arxiv.org",
"tags": [
"Eduardo Paluzo-Hidalgo",
"Yuichi Ike"
],
"textContent": "**Authors:** Eduardo Paluzo-Hidalgo, Yuichi Ike\n\nWe introduce a theoretical framework that connects multi-chart autoencoders in manifold learning with the classical theory of vector bundles and characteristic classes. Rather than viewing autoencoders as producing a single global Euclidean embedding, we treat a collection of locally trained encoder-decoder pairs as a learned atlas on a manifold. We show that any reconstruction-consistent autoencoder atlas canonically defines transition maps satisfying the cocycle condition, and that linearising these transition maps yields a vector bundle coinciding with the tangent bundle when the latent dimension matches the intrinsic dimension of the manifold. This construction provides direct access to differential-topological invariants of the data. In particular, we show that the first Stiefel-Whitney class can be computed from the signs of the Jacobians of learned transition maps, yielding an algorithmic criterion for detecting orientability. We also show that non-trivial characteristic classes provide obstructions to single-chart representations, and that the minimum number of autoencoder charts is determined by the good cover structure of the manifold. Finally, we apply our methodology to low-dimensional orientable and non-orientable manifolds, as well as to a non-orientable high-dimensional image dataset.",
"title": "Learning Tangent Bundles and Characteristic Classes with Autoencoder Atlases"
}