Publications

Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut (2024). Proving linear mode connectivity of neural networks via optimal transport. AISTATS 2024.

Baptiste Goujaud, Céline Moucer, Francois Glineur, Julien Hendrickx, Adrien Taylor, Aymeric Dieuleveut (2024). PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python. Mathematical Programming Computation (MPC).

Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor (2023). On Fundamental Proof Structures in First-Order Optimization. CDC 2023.

Charles Guille-Escuret, Adam Ibrahim, Baptiste Goujaud, Ioannis Mitliagkas (2023). Gradient descent is optimal under lower restricted secant inequality and upper error bound. NeurIPS 2023.

Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor (2023). Counter-examples in first-order optimization: a constructive approach. L-CSS.

Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut (2023). Provable non-accelerations of the heavy-ball method. Opt24 at NeurIPS (oral).

Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien Taylor, Fabian Pedregosa (2022). Super-acceleration with cyclical step-sizes. AISTATS 2022.

Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut (2022). Quadratic minimization: from conjugate gradient to an adaptive Heavy-ball method with Polyak step-sizes. Open Journal of Mathematical Optimization (OJMO).

Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut (2022). Optimal first-order methods for convex functions with a quadratic upper bound.

Charles Guille-Escuret, Baptiste Goujaud, Manuella Girotti, Ioannis Mitliagkas (2021). A Study of Condition Numbers for First-Order Optimization. AISTATS 2021.

Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio (2019). Gradient-based sample selection for online continual learning. NIPS 2019.

Baptiste Goujaud, Eric Tramel, Pierre Courtiol, Mikhail Zaslavskiy, Gilles Wainrib (2018). Robust Detection of Covariate-Treatment Interactions in Clinical Trials. ISCBASC 2018.