AIConfPaper
← Search

Franco Pellegrini

3 accepted papers

2025

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan Dos Santos Costa, Danny Reidenbach, Karsten Kreis, Tomas Geffner +3
ICML 2025poster

Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we bui…

Cited by 0Source ↗PDF ↗Scholar ↗
2022

Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks

Franco Pellegrini, Giulio Biroli
ICML 2022spotlight

Pruning methods can considerably reduce the size of artificial neural networks without harming their performance and in some cases they can even uncover sub-networks that, when trained in isolation, match or surpass the test accuracy of their dense counterparts. Here, we characterize the inductive b…

Cited by 12Source ↗PDF ↗Scholar ↗
2020

An analytic theory of shallow networks dynamics for hinge loss classification

Franco Pellegrini, Giulio Biroli
NeurIPS 2020poster

Neural networks have been shown to perform incredibly well in classification tasks over structured high-dimensional datasets. However, the learning dynamics of such networks is still poorly understood. In this paper we study in detail the training dynamics of a simple type of neural network: a singl…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗