activity
20122026
most citedOn the Number of Experiments Sufficient and in the Worst Case Necessary to Identify All Causal Relations Among N Variables

25 citations · 36 across the 8 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

stat.ML2025

Lower Bounds on the Size of Markov Equivalence Classes

Erik Jahn, Frederick Eberhardt, Leonard J. Schulman

Causal discovery algorithms typically recover causal graphs only up to their Markov equivalence classes unless additional parametric assumptions are made. The sizes of these equiva…

cs.CY2025

Modeling Discrimination with Causal Abstraction

Milan Mossé, Kara Schechtman, Frederick Eberhardt +1

A person is directly racially discriminated against only if her race caused her worse treatment. This implies that race is an attribute sufficiently separable from other attributes…