Scott Pesme

According to our database, Scott Pesme authored at least 8 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Implicit Bias of Mirror Flow on Separable Data.

Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion

CoRR, 2024

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

Hristo Papazov, Scott Pesme, Nicolas Flammarion

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

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

Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion

CoRR, 2023

Saddle-to-Saddle Dynamics in Diagonal Linear Networks.

Scott Pesme, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2021

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

Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Online Robust Regression via SGD on the l1 loss.

Scott Pesme, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion

Proceedings of the 37th International Conference on Machine Learning, 2020