Baptiste Goujaud

14 papers A* 2A 3Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?
CoRR
Si Yi Meng, Baptiste Goujaud, Antonio Orvieto, Christopher De Sa
2024 J jnl
PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python.
Math. Program. Comput.
Baptiste Goujaud, Céline Moucer, François Glineur, Julien M. Hendrickx, Adrien B. Taylor, Aymeric Dieuleveut
2024 A conf
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport.
AISTATS
Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
2024 J jnl
Short Paper - Quadratic minimization: from conjugate gradient to an adaptive Polyak's momentum method with Polyak step-sizes.
Open J. Math. Optim.
Baptiste Goujaud, Adrien B. Taylor, Aymeric Dieuleveut
2023 J jnl
Counter-Examples in First-Order Optimization: A Constructive Approach.
IEEE Control. Syst. Lett.
Baptiste Goujaud, Aymeric Dieuleveut, Adrien B. Taylor
2023 — conf
On Fundamental Proof Structures in First-Order Optimization.
CDC
Baptiste Goujaud, Aymeric Dieuleveut, Adrien B. Taylor
2023 J jnl
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport.
CoRR
Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
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
PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python.
CoRR
Baptiste Goujaud, Céline Moucer, François Glineur, Julien M. Hendrickx, Adrien B. Taylor, Aymeric Dieuleveut
2022 A conf
Super-Acceleration with Cyclical Step-sizes.
AISTATS
Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien B. Taylor, Fabian Pedregosa
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 A* conf
Gradient based sample selection for online continual learning.
NeurIPS
Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio
2019 J jnl
Online continual learning with no task boundaries.
CoRR
Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio