Biblio Discovery — Demo Discovery Service

2 hasil untuk "Defilippis, Leonardo"

Menampilkan 1–2 · 0,27 detik · RSS

  1. Preprint Teks lengkap

    Optimal scaling laws in learning hierarchical multi-index models

    Defilippis, Leonardo; Krzakala, Florent; Loureiro, Bruno dkk.

    arXiv · 2026 · Inggris · arXiv

    In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws for subspace recovery and prediction error, revealing how…

  2. Preprint Teks lengkap

    A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models

    Defilippis, Leonardo; Krzakala, Florent; Loureiro, Bruno dkk.

    arXiv · 2026 · Inggris · arXiv

    Understanding when learning is statistically possible yet computationally hard is a central challenge in high-dimensional statistics. In this work, we investigate this question in the context of single- and multi-index models, classes of functions widely studied as benchmarks to probe the ability…