Back
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
@conference{Meterezetal24, title = {Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion}, booktitle = {The Twelfth International Conference on Learning Representations (ICLR)}, month = may, year = {2024}, note = {*equal contribution}, slug = {meterezetal24}, author = {Meterez*, A. and Joudaki*, A. and Orabona, F. and Immer, A. and R{\"a}tsch, G. and Daneshmand, H.}, month_numeric = {5} }