2 papers
q-fin.RM2026
Adapted Law Invariance and Time-Consistent Dynamic Risk Measures
Mathias Beiglböck, Silvana M. Pesenti, Maxime Sylvestre
In static risk measurement, law invariance expresses the principle that the risk of a position should depend only on its distribution, and not on the particular probability space o…
stat.ML2024
Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
Tom Sander, Maxime Sylvestre, Alain Durmus
Training Deep Neural Networks (DNNs) with small batches using Stochastic Gradient Descent (SGD) yields superior test performance compared to larger batches. The specific noise stru…