Skipping boundary matrix reduction and using unreduced persistence diagrams as ML features gives on-par or better task performance with large memory savings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unreduced Persistence Diagrams for Topological Machine Learning
Skipping boundary matrix reduction and using unreduced persistence diagrams as ML features gives on-par or better task performance with large memory savings.