TopoFisher optimizes trainable filtrations, vectorizations, and compressors in persistent homology to maximize Fisher information, yielding higher information than fixed cosmological summaries and approaching neural baselines with far fewer parameters while generalizing better under simulator shifts
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Derives new analytical sample size formulas for the marginal hazard ratio under IPW estimation in Cox models, correcting classic log-rank formulas for RCTs and adding an overlap measure for observational data.
citing papers explorer
-
TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
TopoFisher optimizes trainable filtrations, vectorizations, and compressors in persistent homology to maximize Fisher information, yielding higher information than fixed cosmological summaries and approaching neural baselines with far fewer parameters while generalizing better under simulator shifts
-
Sample size and power calculations for causal inference with time-to-event outcomes
Derives new analytical sample size formulas for the marginal hazard ratio under IPW estimation in Cox models, correcting classic log-rank formulas for RCTs and adding an overlap measure for observational data.