Showing 2026Show all
3 papers · 1 filter
cs.LG2026
A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks
Pankhil Gawade, Kirsten Fischer, Guy Wolf +1
How depth and width of neural networks shape learned representations is usually studied only after training. We show that, in a tractable feature-learning setting, this dependence…
cs.LG2026
Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
Adrien Aumon, Myriam Lizotte, Guy Wolf +2
Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. How…
cs.LG2026
Revisiting Forest Proximities via Sparse Leaf-Incidence Kernels
Adrien Aumon, Guy Wolf, Kevin R. Moon +1
Decision forests induce supervised similarities through the partition structure of their trees. Yet forest proximity computation is still often treated as a quadratic operation in…