6 citations · 12 across the 11 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Monitoring Neural Training with Topology: A Footprint-Predictable Collapse Index
Alexander Kalinowski
Representational collapse, where embeddings become anisotropic and lose multi-scale structure, can erode downstream performance long before performance metrics react. We propose an…
cs.CG2026
Calibrated Persistent Homology Tests for High-dimensional Collapse Detection
Alexander Kalinowski
We study detection of collapse in high-dimensional point clouds, where mass concentrates near a lower-dimensional set relative to a non-collapsed geometry. We propose persistent ho…