2 papers
cs.LG2025
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
Qiaoyue Tang, Alain Zhiyanov, Mathias Lécuyer
In this work, we analyze the optimization behaviour of common private learning optimization algorithms under heavy-tail class imbalanced distribution. We show that, in a stylized m…
cs.LG2024
Training and Evaluating Causal Forecasting Models for Time-Series
Thomas Crasson, Yacine Nabet, Mathias Lécuyer
Deep learning time-series models are often used to make forecasts that inform downstream decisions. Since these decisions can differ from those in the training set, there is an imp…