Notice détaillée
Titre
SPOC1
Formal Name (French)
Laboratoire de physique statistique des systèmes computationnels (SB/IC)
Formal Name (English)
Statistical Physics of Computation Laboratory (SB/IC)
Lab Manager
Zdeborova, Lenka
Group ID
U13823
Auteurs affilié
Alarcon, Angeles
Behrens, Freya
Biggio, Luca
Clarte, Lucas Andry
Cui, Hugo Chao
Dalle, Guillaume
Dandi, Yatin
Duranthon, Odilon
Erba, Vittorio
Gerace, Federica
Keup, Christian
Koller, Cédric Xavier
Piccioli, Giovanni
Saglietti, Luca
Troiani, Emanuele
Vandenbroucque, Adrien
Wu, Zhengqing
Zdeborová, Lenka
Behrens, Freya
Biggio, Luca
Clarte, Lucas Andry
Cui, Hugo Chao
Dalle, Guillaume
Dandi, Yatin
Duranthon, Odilon
Erba, Vittorio
Gerace, Federica
Keup, Christian
Koller, Cédric Xavier
Piccioli, Giovanni
Saglietti, Luca
Troiani, Emanuele
Vandenbroucque, Adrien
Wu, Zhengqing
Zdeborová, Lenka
Institut
IPHYS
Faculté
SB
Lien extérieur
https://iphys.epfl.ch/
Publications
(Dis)assortative partitions on random regular graphs
Construction of optimal spectral methods in phase retrieval
Expectation consistency for calibration of neural networks
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
Multi-layer state evolution under random convolutional design
On double-descent in uncertainty quantification in overparametrized models
Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
Tree-AMP: Compositional Inference with Tree Approximate Message Passing
Voir toutes les publications (44)
Construction of optimal spectral methods in phase retrieval
Expectation consistency for calibration of neural networks
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
Multi-layer state evolution under random convolutional design
On double-descent in uncertainty quantification in overparametrized models
Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
Tree-AMP: Compositional Inference with Tree Approximate Message Passing
Voir toutes les publications (44)
Le document apparaît dans
Authorities > Lab