MaxSketch achieves O~(log n / ε²) memory for (1+ε)-approximate distinct counting in streams with geometric structure via max-linear random projections.
Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 117(40):24652–24663
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
StructAlign uses simplex ETF geometry and cross-modal relation-preserving losses to mitigate intra- and cross-modal feature drift in continual text-to-video retrieval.
Strong superposition causes neural loss to scale as the inverse of model dimension due to geometric feature overlaps, explaining scaling laws for broad frequency distributions.
citing papers explorer
-
MaxSketch: Robust Distinct Counting in Streams via Random Projections
MaxSketch achieves O~(log n / ε²) memory for (1+ε)-approximate distinct counting in streams with geometric structure via max-linear random projections.
-
StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval
StructAlign uses simplex ETF geometry and cross-modal relation-preserving losses to mitigate intra- and cross-modal feature drift in continual text-to-video retrieval.
-
Superposition Yields Robust Neural Scaling
Strong superposition causes neural loss to scale as the inverse of model dimension due to geometric feature overlaps, explaining scaling laws for broad frequency distributions.