Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
Nikos Tsikouras, Yorgos Pantis, Ioannis Mitliagkas +1
Understanding the dynamics of feature learning in neural networks (NNs) remains a significant challenge. The work of (Mousavi-Hosseini et al., 2023) analyzes a multiple index teach…
stat.ML2024
Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala
Understanding the mechanisms through which neural networks extract statistics from input-label pairs through feature learning is one of the most important unsolved problems in supe…