EUROPT 2024
Abstract Submission

Session WD-3: Optimization in neural architectures II in stream Optimization in neural architectures: convergence and solution characterization

Wednesday, 11:25 - 12:40
Room: M:J

Session chair(s):
Maria-Luiza Vladarean (maria-luiza.vladarean@epfl.ch)
Manish Krishan Lal (manish.krishanlal@tum.de)

The following abstracts have been submitted in this session:
155. Vanishing Gradients in Reinforcement Finetuning of Language Models Noam Razin [] - Israel
accepted
164. A phase transition between positional and semantic learning in a solvable model of dot-product attention Hugo Cui [] - Switzerland
accepted
Freya Behrens [] - Switzerland
Florent Krzakala [] - Switzerland
Lenka Zdeborová [] - Switzerland
151. On the spectral bias of two-layer linear networks Aditya Varre [] - Switzerland
accepted