Showing 2026Show all
2 papers · 1 filter
cs.LG2026
The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
Connall Garrod, Jonathan P. Keating, Christos Thrampoulidis
Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architec…
cs.LG2026
When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating +1
Backdoor poisoning attacks behave counter-intuitively in high dimensions: stronger training triggers can help the defender. We study regularised generalised linear models on Gaussi…