Source Themes

Proving linear mode connectivity of neural networks via optimal transport
Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
Baptiste Goujaud, Céline Moucer, Francois Glineur, Julien Hendrickx, Adrien Taylor, Aymeric Dieuleveut
Counter-examples in first-order optimization: a constructive approach
Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor
Gradient descent is optimal under lower restricted secant inequality and upper error bound
Charles Guille-Escuret, Adam Ibrahim, Baptiste Goujaud, Ioannis Mitliagkas
On Fundamental Proof Structures in First-Order Optimization
Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor
Provable non-accelerations of the heavy-ball method
( ) (Create your slides in Markdown - click the Slides button to check out the example.) ( ) () (Add the publication’s full text or supplementary notes here. You can use rich formatting such as including [code, math, and images](https://docs.
Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
Quadratic minimization: from conjugate gradient to an adaptive Heavy-ball method with Polyak step-sizes
Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
Super-acceleration with cyclical step-sizes
Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien Taylor, Fabian Pedregosa
Optimal first-order methods for convex functions with a quadratic upper bound
Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
A Study of Condition Numbers for First-Order Optimization
Charles Guille-Escuret, Baptiste Goujaud, Manuella Girotti, Ioannis Mitliagkas