activity
20202026
most citedOnline Robust Regression via SGD on the l1 loss

12 citations · 17 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

MAP Estimation with Denoisers: Convergence Rates and Guarantees

Scott Pesme, Giacomo Meanti, Michael Arbel +1

Denoiser models have become powerful tools for inverse problems, enabling the use of pretrained networks to approximate the score of a smoothed prior distribution. These models are…

cs.LG2025

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

Etienne Boursier, Scott Pesme, Radu-Alexandru Dragomir

We study the dynamics of gradient flow with small weight decay on general training losses . Under mild regularity assumptions and assuming convergen…

cs.LG2024

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Hristo Papazov, Scott Pesme, Nicolas Flammarion

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient…

cs.LG2023

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Scott Pesme, Nicolas Flammarion

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively…

cs.LG2023

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

Mathieu Even, Scott Pesme, Suriya Gunasekar +1

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over dia…

cs.LG20205 cited

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion

Constant step-size Stochastic Gradient Descent exhibits two phases: a transient phase during which iterates make fast progress towards the optimum, followed by a stationary phase d…