5 papers
Score Distributions, Not Cells: Evaluating Single-Cell Perturbations Under Class Overlap
Youssef Marrakchi, Davide D'Ascenzo, Sebastiano Cultrera di Montesano
Most classification problems assume the classes are roughly separable, so that an individual sample can usually be assigned to one class. Single-cell perturbation data violates thi…
scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
Davide D'Ascenzo, Sebastiano Cultrera di Montesano
Training deep learning models on single-cell datasets with hundreds of millions of cells requires loading data from disk, as these datasets exceed available memory. While random sa…
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
Andrea Gurioli, Davide D'Ascenzo, Federico Pennino +2
Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authors…
When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
April Chan, Davide D'Ascenzo, Sebastiano Cultrera di Montesano
Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances th…
Position: A Theory of Deep Learning Must Include Compositional Sparsity
David A. Danhofer, Davide D'Ascenzo, Rafael Dubach +1
Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the cu…