Charles Guille-Escuret

15 papers A* 4A 1Journal 10
YearRankTypeTitle / Venue / Authors
2025 J jnl
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training.
CoRR
Oleksiy Ostapenko, Charles Guille-Escuret, Luke Kumar, Max Tian, Denis Kocetkov, Gopeshh Subbaraj, Raymond Li, Joel Lamy-Poirier, Sébastien Paquet, Torsten Scholak
2024 A* conf
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection.
NeurIPS
Charles Guille-Escuret, Pierre-André Noël, Ioannis Mitliagkas, David Vázquez, João Monteiro
2024 J jnl
Finite Sample Confidence Regions for Linear Regression Parameters Using Arbitrary Predictors.
CoRR
Charles Guille-Escuret, Eugène Ndiaye
2024 J jnl
From Conformal Predictions to Confidence Regions.
CoRR
Charles Guille-Escuret, Eugène Ndiaye
2024 A* conf
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths.
ICML
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras, Ioannis Mitliagkas
2024 J jnl
Understanding Adam Requires Better Rotation Dependent Assumptions.
CoRR
Lucas Maes, Tianyue H. Zhang, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret
2023 A* conf
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning.
NeurIPS
Charles Guille-Escuret, Pau Rodríguez, David Vázquez, Ioannis Mitliagkas, João Monteiro
2023 J jnl
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection.
CoRR
Charles Guille-Escuret, Pierre-André Noël, Ioannis Mitliagkas, David Vázquez, João Monteiro
2023 J jnl
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths.
CoRR
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras, Ioannis Mitliagkas
2022 J jnl
CADet: Fully Self-Supervised Anomaly Detection With Contrastive Learning.
CoRR
Charles Guille-Escuret, Pau Rodríguez, David Vázquez, Ioannis Mitliagkas, João Monteiro
2022 A* conf
Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound.
NeurIPS
Charles Guille-Escuret, Adam Ibrahim, Baptiste Goujaud, Ioannis Mitliagkas
2022 J jnl
Towards Out-of-Distribution Adversarial Robustness.
CoRR
Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas, Irina Rish, David Krueger, Pouya Bashivan
2021 A conf
A Study of Condition Numbers for First-Order Optimization.
AISTATS
Charles Guille-Escuret, Manuela Girotti, Baptiste Goujaud, Ioannis Mitliagkas
2020 J jnl
A Study of Condition Numbers for First-Order Optimization.
CoRR
Charles Guille-Escuret, Baptiste Goujaud, Manuela Girotti, Ioannis Mitliagkas
2019 J jnl
InsectUp: Crowdsourcing Insect Observations to Assess Demographic Shifts and Improve Classification.
CoRR
Léonard Boussioux, Tomás Giro-Larraz, Charles Guille-Escuret, Mehdi Cherti, Balázs Kégl