| 2025 | ICML | The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training. | Fabian Schaipp, Alexander Hgele, Adrien B. Taylor, Umut Simsekli, Francis Bach |
| 2024 | ICLR | Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning. | Antoine Bambade, Fabian Schramm, Adrien B. Taylor, Justin Carpentier |
| 2023 | ICML | Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity. | Eduard Gorbunov, Adrien B. Taylor, Samuel Horvth, Gauthier Gidel |
| 2022 | AISTATS | Super-Acceleration with Cyclical Step-sizes. | Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien B. Taylor, Fabian Pedregosa |
| 2020 | COLT | Complexity Guarantees for Polyak Steps with Momentum. | Mathieu Barr, Adrien B. Taylor, Alexandre d'Aspremont |
| 2019 | COLT | Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions. | Adrien B. Taylor, Francis R. Bach |
| 2018 | ICML | Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees. | Adrien B. Taylor, Bryan Van Scoy, Laurent Lessard |