activity
20242026
most citedGradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

2 citations · 2 across the 1 of their papers we have counts for

collaborators

6 papers

stat.ML20262 cited

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion

The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its su…

cs.LG2025

Early alignment in two-layer networks training is a two-edged sword

Etienne Boursier, Nicolas Flammarion

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small i…

stat.ML2025

Long-Context Linear System Identification

Oğuz Kaan Yüksel, Mathieu Even, Nicolas Flammarion

This paper addresses the problem of long-context linear system identification, where the state of a dynamical system at time depends linearly on previous states ove…

cs.LG2025

Simplicity bias and optimization threshold in two-layer ReLU networks

Etienne Boursier, Nicolas Flammarion

Understanding generalization of overparametrized neural networks remains a fundamental challenge in machine learning. Most of the literature mostly studies generalization from an i…

stat.ML2025

Penalising the biases in norm regularisation enforces sparsity

Etienne Boursier, Nicolas Flammarion

Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between regularising parameters' norm and ob…

stat.ML2024

Implicit Bias of Mirror Flow on Separable Data

Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion

We examine the continuous-time counterpart of mirror descent, namely mirror flow, on classification problems which are linearly separable. Such problems are minimised `at infinity'…