← Search

MARIA FONOBEROVA

2 accepted papers

2024

Identifying Equivalent Training Dynamics

NeurIPS 2024spotlight

Study of the nonlinear evolution deep neural network (DNN) parameters undergo during training has uncovered regimes of distinct dynamical behavior. While a detailed understanding of these phenomena has the potential to advance improvements in training efficiency and robustness, the lack of methods f…

2022

An Operator Theoretic View On Pruning Deep Neural Networks

ICLR 2022poster

The discovery of sparse subnetworks that are able to perform as well as full models has found broad applied and theoretical interest. While many pruning methods have been developed to this end, the naïve approach of removing parameters based on their magnitude has been found to be as robust as more…

Cited by 16SourcePDFScholar