4 papers
On the Role of Reversible Instance Normalization
Gaspard Berthelier, Tahar Nabil, Etienne Le Naour +3
Data normalization is a crucial component of deep learning models, yet its role in time series forecasting remains insufficiently understood. In this paper, we identify three centr…
Variance-Reduced Unlearning using Forget Set Gradients
Martin Van Waerebeke, Marco Lorenzi, Kevin Scaman +2
In machine unlearning, unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the fo…
When to Forget? Complexity Trade-offs in Machine Unlearning
Martin Van Waerebeke, Marco Lorenzi, Giovanni Neglia +1
Machine Unlearning (MU) aims at removing the influence of specific data points from a trained model, striving to achieve this at a fraction of the cost of full model retraining. In…
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
Batiste Le Bars, Aurélien Bellet, Marc Tommasi +2
This paper presents a new generalization error analysis for Decentralized Stochastic Gradient Descent (D-SGD) based on algorithmic stability. The obtained results overhaul a series…