Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
Tom Sander, Maxime Sylvestre, Alain Durmus. Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training. International Conference on Artificial Intelligence and Statistics (AISTATS). Feb, 2024.
TAN Without a Burn: Scaling Laws of DP-SGD
Tom Sander, Pierre Stock, Alexandre Sablayrolles. TAN Without a Burn: Scaling Laws of DP-SGD. International Conference of Machine Learning (ICML). Jul, 2023.