Scott Pesme

Most-cited papers

1. Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity

   Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion

   2021Neural Information Processing Systems138 citations

   Semantic Scholar

   Save

2. Saddle-to-saddle dynamics in diagonal linear networks

   Scott Pesme, Nicolas Flammarion

   2023Neural Information Processing Systems72 citations Open access

   Semantic Scholar

   Save

3. (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability

   Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion

   2023Neural Information Processing Systems42 citations

   Semantic Scholar

   Save

4. Online Robust Regression via SGD on the l1 loss

   Scott Pesme, Nicolas Flammarion

   2020Neural Information Processing Systems41 citations

   Semantic Scholar

   Save

5. (S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability

   Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion

   2023arXiv.org29 citations Open access

   Semantic Scholar

   Save

6. On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

   Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion

   2020International Conference on Machine Learning19 citations

   Semantic Scholar

   Save

7. A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation

   Etienne Boursier, Scott Pesme, Radu-Alexandru Dragomir

   2025Neural Information Processing Systems13 citations

   Semantic Scholar

   Save

8. Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

   Hristo Papazov, Scott Pesme, Nicolas Flammarion

   2024International Conference on Artificial Intelligence and Statistics12 citations

   Semantic Scholar

   Save

9. Implicit Bias of Mirror Flow on Separable Data

   Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion

   2024Neural Information Processing Systems10 citations

   Semantic Scholar

   Save

10. MAP Estimation with Denoisers: Convergence Rates and Guarantees

    Scott Pesme, Giacomo Meanti, M. Arbel, Julien Mairal

    2025Neural Information Processing Systems6 citations

    Semantic Scholar

    Save

11. Beyond MMSE: Enhancing PnP Restoration with ProxiMAP

    Kenta Vert, Giacomo Meanti, Scott Pesme, Michael Arbel +1 more

    2026arXiv.org2 citations

    Semantic Scholar

    Save

12. GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability

    Mathieu Even, Scott Pesme, Epfl Suriya Gunasekar, Nicolas Flammarion

    0 citations

    Semantic Scholar

    Save