{"ID":2896063,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07625","arxiv_id":"2507.07625","title":"Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials","abstract":"We prove concentration inequalities for several models of non-linear random matrices. As corollaries we obtain estimates for linear spectral statistics of the conjugate kernel of neural networks and non-commutative polynomials in (possibly dependent) random matrices.","short_abstract":"We prove concentration inequalities for several models of non-linear random matrices. As corollaries we obtain estimates for linear spectral statistics of the conjugate kernel of neural networks and non-commutative polynomials in (possibly dependent) random matrices.","url_abs":"https://arxiv.org/abs/2507.07625","url_pdf":"https://arxiv.org/pdf/2507.07625v2","authors":"[\"Radosław Adamczak\"]","published":"2025-07-10T10:47:42Z","proceeding":"math.PR","tasks":"[\"math.PR\",\"cs.LG\"]","methods":"[]","has_code":false}