Beaglehole, Daniel

6 publications

ICML 2025 Emergence in Non-Neural Models: Grokking Modular Arithmetic via Average Gradient Outer Product Neil Rohit Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

NeurIPS 2024 Average Gradient Outer Product as a Mechanism for Deep Neural Collapse Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin

NeurIPSW 2024 Emergence in Non-Neural Models: Grokking Modular Arithmetic via Average Gradient Outer Product Neil Rohit Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

TMLR 2024 Feature Learning as Alignment: A Structural Property of Gradient Descent in Non-Linear Neural Networks Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala

ICMLW 2024 Gradient Descent Induces Alignment Between Weights and the Pre-Activation Tangents for Deep Non-Linear Networks Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala

ICML 2022 Learning to Hash Robustly, Guaranteed Alexandr Andoni, Daniel Beaglehole