A sheaf-theoretic framework for causal abstraction networks that represents and learns consistent collections of mixture causal models across distributed agents.
Distributed optimization and statistical learning via the alternating direction method of multipliers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Networks of Causal Abstractions: A Sheaf-theoretic Framework
A sheaf-theoretic framework for causal abstraction networks that represents and learns consistent collections of mixture causal models across distributed agents.