6 papers
Constrained Variable Projection for Structured Problems
Emanuele Zangrando, Sara Venturini, Francesco Rinaldi +1
Variable projection is a classical technique for separable nonlinear least-squares problems, in which variables that enter linearly are eliminated exactly, yielding a reduced nonli…
Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
Pietro Sittoni, Emanuele Zangrando, Angelo A. Casulli +2
Deep learning-based methods have shown remarkable effectiveness in solving PDEs, largely due to their ability to enable fast simulations once trained. However, despite the availabi…
Provable Emergence of Deep Neural Collapse and Low-Rank Bias in -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…
GeoLoRA: Geometric integration for parameter efficient fine-tuning
Steffen Schotthöfer, Emanuele Zangrando, Gianluca Ceruti +2
Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face se…
Low-Rank Adversarial PGD Attack
Dayana Savostianova, Emanuele Zangrando, Francesco Tudisco
Adversarial attacks on deep neural network models have seen rapid development and are extensively used to study the stability of these networks. Among various adversarial strategie…
Geometry-aware training of factorized layers in tensor Tucker format
Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti +2
Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during training and inference phases. Given…