Publication
A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
Publications associées (39)
Random matrix methods for high-dimensional machine learning models
In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...
EPFL2024Neural Distributed Image Compression with Cross-Attention Feature Alignment
We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...
IEEE COMPUTER SOC2023Deep Learning Generalization with Limited and Noisy Labels
Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...
EPFL2023Dual-frequency spectral radar retrieval of snowfall microphysics: a physics-driven deep-learning approach
The use of meteorological radars to study snowfall microphysical properties and processes is well established, in particular via a few distinct techniques: the use of radar polarimetry, of multi-frequency radar measurements, and of the radar Doppler spectr ...
COPERNICUS GESELLSCHAFT MBH2023Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks
This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits.In the ...
EPFL2023Robust Training and Verification of Deep Neural Networks
According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...
EPFL2023Leveraging Unlabeled Data to Track Memorization
Patrick Thiran, Mahsa Forouzesh, Hanie Sedghi
Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, ca ...
2023Benign Overfitting in Deep Neural Networks under Lazy Training
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...
2023Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design
Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti, Liang Xu
Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...
2023Neural ADMIXTURE for rapid genomic clustering
Characterizing the genetic structure of large cohorts has become increasingly important as genetic studies extend to massive, increasingly diverse biobanks. Popular methods decompose individual genomes into fractional cluster assignments with each cluster ...
SPRINGERNATURE2023