Simone Brugiapaglia

activity

20202026

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Approximating Matrix Functions with Deep Neural Networks and Transformers

Rahul Padmanabhan, Simone Brugiapaglia

Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, w…

cs.LG2024

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^{2}$ -Regularized Nonlinear Networks

Emanuele Zangrando, Piero Deidda, Simone Brugiapaglia +2

We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained wit…

Approximating Matrix Functions with Deep Neural Networks and Transformers

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in L2-Regularized Nonlinear Networks

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^{2}$ -Regularized Nonlinear Networks