activity
20202022
most citedPerturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

26 citations · 94 across the 8 of their papers we have counts for

collaborators

9 papers

cond-mat.dis-nn2022★ 9 cited

(Dis)assortative Partitions on Random Regular Graphs

Freya Behrens, Gabriel Arpino, Yaroslav Kivva +1

We study the problem of assortative and disassortative partitions on random -regular graphs. Nodes in the graph are partitioned into two non-empty groups. In the assortative par…

cs.LG2022★ 6 cited

Theoretical characterization of uncertainty in high-dimensional linear classification

Lucas Clarté, Bruno Loureiro, Florent Krzakala +1

Being able to reliably assess not only the \emph{accuracy} but also the \emph{uncertainty} of models' predictions is an important endeavour in modern machine learning. Even if the…

stat.ML2022★ 11 cited

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro +2

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically differ…

stat.ML2022★ 5 cited

Error Scaling Laws for Kernel Classification under Source and Capacity Conditions

Hugo Cui, Bruno Loureiro, Florent Krzakala +1

We consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they…

cs.IT2021★ 13 cited

Aligning random graphs with a sub-tree similarity message-passing algorithm

Giovanni Piccioli, Guilhem Semerjian, Gabriele Sicuro +1

The problem of aligning Erdös-Rényi random graphs is a noisy, average-case version of the graph isomorphism problem, in which a pair of correlated random graphs is observed through…

cond-mat.dis-nn2021★ 26 cited

Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

Antoine Maillard, Florent Krzakala, Marc Mézard +1

Factorization of matrices where the rank of the two factors diverges linearly with their sizes has many applications in diverse areas such as unsupervised representation learning,…