Cedric Gerbelot
5 papers · 2020–2022 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🗺️
Taxonomy Completionist
(12)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
NIPS (3)
COLT (1)
ICML (1)
Top co-authors
Keywords
generalization error
(2)
message passing
(2)
high-dimensional statistics
(2)
convex loss
(2)
approximate message passing
(1)
multi-class classification
(1)
high-dimensional analysis
(1)
kernel regression
(1)
signal recovery
(1)
elastic net
(1)
penalized regression
(1)
state evolution
(1)
generative model
(1)
convolutional neural network
(1)
generalized linear model
(1)
feature map
(1)
generative prior
(1)
learning curve
(1)
bias variance tradeoff
(1)
empirical risk minimisation
(1)
Papers
Multi-layer State Evolution Under Random Convolutional Design
NIPS 2022
Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
ICML 2022
Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions
NIPS 2021
Learning curves of generic features maps for realistic datasets with a teacher-student model
NIPS 2021
Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices
COLT 2020