{"ID":2837803,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19703","arxiv_id":"2511.19703","title":"The Alexander-Hirschowitz theorem for neurovarieties","abstract":"We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.","short_abstract":"We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.","url_abs":"https://arxiv.org/abs/2511.19703","url_pdf":"https://arxiv.org/pdf/2511.19703v1","authors":"[\"A. Massarenti\",\"M. Mella\"]","published":"2025-11-24T21:09:42Z","proceeding":"math.AG","tasks":"[\"math.AG\",\"cs.AI\",\"cs.LG\",\"math.AC\"]","methods":"[]","has_code":false}