Publications associées à System and method for privacy-preserving distributed training of neural network models on distributed datasets

Deep Learning Theory Through the Lens of Diagonal Linear Networks

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

EPFL Infoscience2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Hristo Georgiev Papazov, Scott William Pesme

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

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 ...

EPFL2023

Probabilistic methods for neural combinatorial optimization

Nikolaos Karalias

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

EPFL2023

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

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 ...

EPFL2023

Polynomial-time universality and limitations of deep learning

Emmanuel Abbé

The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...

WILEY2023

Supervised learning and inference of spiking neural networks with temporal coding

Ana Stanojevic

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

EPFL2023

Predicting nonlinear optical scattering with physics-driven neural networks

Demetri Psaltis, Carlo Gigli, Ahmed Ayoub

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

AIP Publishing2023

System and method for privacy-preserving distributed training of neural network models on distributed datasets

Graph Chatbot

Chattez avec Graph Search

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Deep Learning Generalization with Limited and Noisy Labels

Probabilistic methods for neural combinatorial optimization

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Polynomial-time universality and limitations of deep learning

Supervised learning and inference of spiking neural networks with temporal coding

Predicting nonlinear optical scattering with physics-driven neural networks

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Polynomial-time universality and limitations of deep learning

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Probabilistic methods for neural combinatorial optimization

Deep Learning Generalization with Limited and Noisy Labels

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Supervised learning and inference of spiking neural networks with temporal coding

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Predicting nonlinear optical scattering with physics-driven neural networks