Search Results for author: Marco Lorenzi

Found 26 papers, 14 papers with code

Tackling the dimensions in imaging genetics with CLUB-PLS

no code implementations13 Sep 2023 Andre Altmann, Ana C Lawry Aguila, Neda Jahanshad, Paul M Thompson, Marco Lorenzi

The standard approach in the area are mass univariate analyses across genetic factors and imaging phenotypes.

On Tail Decay Rate Estimation of Loss Function Distributions

1 code implementation5 Jun 2023 Etrit Haxholli, Marco Lorenzi

The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem.

Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows

no code implementations5 Jun 2023 Etrit Haxholli, Marco Lorenzi

Furthermore, we derive the Jacobian determinant of the general augmented form by generalizing the chain rule in the continuous sense into the Cable Rule, which expresses the forward sensitivity of ODEs with respect to their initial conditions.

Density Estimation

Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching

no code implementations5 Jun 2023 Etrit Haxholli, Marco Lorenzi

In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potentially impede modeling flexibility and capacity.

Density Estimation

Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications

1 code implementation24 Apr 2023 Francesco Cremonesi, Marc Vesin, Sergen Cansiz, Yannick Bouillard, Irene Balelli, Lucia Innocenti, Santiago Silva, Samy-Safwan Ayed, Riccardo Taiello, Laetita Kameni, Richard Vidal, Fanny Orlhac, Christophe Nioche, Nathan Lapel, Bastien Houis, Romain Modzelewski, Olivier Humbert, Melek Önen, Marco Lorenzi

The real-world implementation of federated learning is complex and requires research and development actions at the crossroad between different domains ranging from data science, to software programming, networking, and security.

Federated Learning

Fed-MIWAE: Federated Imputation of Incomplete Data via Deep Generative Models

no code implementations17 Apr 2023 Irene Balelli, Aude Sportisse, Francesco Cremonesi, Pierre-Alexandre Mattei, Marco Lorenzi

In addition, thanks to the variational nature of Fed-MIWAE, our method is designed to perform multiple imputation, allowing for the quantification of the imputation uncertainty in the federated scenario.

Federated Learning Imputation

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

1 code implementation21 Nov 2022 Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni, Marco Lorenzi

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure.

Machine Unlearning

A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates

no code implementations21 Jun 2022 Yann Fraboni, Richard Vidal, Laetitia Kameni, Marco Lorenzi

We show that our general framework applies to existing optimization schemes including centralized learning, FedAvg, asynchronous FedAvg, and FedBuff.

Federated Learning

Privacy Preserving Image Registration

2 code implementations17 May 2022 Riccardo Taiello, Melek Önen, Francesco Capano, Olivier Humbert, Marco Lorenzi

Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame.

Affine Image Registration Cubic splines Image Registration +2

A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations

no code implementations15 Apr 2022 Irene Balelli, Santiago Silva, Marco Lorenzi

Our method is expressed through a hierarchical Bayesian latent variable model, where client-specific parameters are assumed to be realization from a global distribution at the master level, which is in turn estimated to account for data bias and variability across clients.

Federated Learning

A General Theory for Client Sampling in Federated Learning

1 code implementation26 Jul 2021 Yann Fraboni, Richard Vidal, Laetitia Kameni, Marco Lorenzi

In this work, we provide a general theoretical framework to quantify the impact of a client sampling scheme and of the clients heterogeneity on the federated optimization.

Federated Learning

Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas

1 code implementation30 Apr 2021 Adrià Casamitjana, Marco Lorenzi, Sebastiano Ferraris, Loc Peter, Marc Modat, Allison Stevens, Bruce Fischl, Tom Vercauteren, Juan Eugenio Iglesias

The model relies on a spanning tree of latent transforms connecting all the sections and slices of the reference volume, and assumes that the registration between any pair of images can be see as a noisy version of the composition of (possibly inverted) latent transforms connecting the two images.

3D Reconstruction Bayesian Inference

Joint data imputation and mechanistic modelling for simulating heart-brain interactions in incomplete datasets

no code implementations2 Oct 2020 Jaume Banus, Maxime Sermesant, Oscar Camara, Marco Lorenzi

To tackle this problem we introduce a probabilistic framework for joint cardiac data imputation and personalisation of cardiovascular mechanistic models, with application to brain studies with incomplete heart data.

Anatomy Imputation

Free-rider Attacks on Model Aggregation in Federated Learning

1 code implementation21 Jun 2020 Yann Fraboni, Richard Vidal, Marco Lorenzi

Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without actually contributing with any data.

Federated Learning

A model of brain morphological changes related to aging and Alzheimer's disease from cross-sectional assessments

no code implementations23 May 2019 Raphaël Sivera, Hervé Delingette, Marco Lorenzi, Xavier Pennec, Nicholas Ayache

In this study we propose a deformation-based framework to jointly model the influence of aging and Alzheimer's disease (AD) on the brain morphological evolution.

Monotonic Gaussian Process for Spatio-Temporal Disease Progression Modeling in Brain Imaging Data

no code implementations28 Feb 2019 Clement Abi Nader, Nicholas Ayache, Philippe Robert, Marco Lorenzi

We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from series of high-dimensional brain images.

blind source separation Gaussian Processes

Modeling and inference of spatio-temporal protein dynamics across brain networks

2 code implementations18 Jan 2019 Sara Garbarino, Marco Lorenzi

Models of misfolded proteins (MP) aim at discovering the bio-mechanical propagation properties of neurological diseases (ND) by identifying plausible associated dynamical systems.

Uncertainty Quantification Variational Inference

Disease Knowledge Transfer across Neurodegenerative Diseases

2 code implementations11 Jan 2019 Razvan V. Marinescu, Marco Lorenzi, Stefano B. Blumberg, Alexandra L. Young, Pere P. Morell, Neil P. Oxtoby, Arman Eshaghi, Keir X. Yong, Sebastian J. Crutch, Polina Golland, Daniel C. Alexander

DKT infers robust multimodal biomarker trajectories in rare neurodegenerative diseases even when only limited, unimodal data is available, by transferring information from larger multimodal datasets from common neurodegenerative diseases.

Transfer Learning

Constraining the Dynamics of Deep Probabilistic Models

no code implementations ICML 2018 Marco Lorenzi, Maurizio Filippone

We introduce a novel generative formulation of deep probabilistic models implementing "soft" constraints on their function dynamics.

Uncertainty Quantification Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.