skip to content

Statistical Laboratory

Structural causal models are powerful tools for understanding algorithmic fairness. Strong causal assumptions can be more interpretable and enable transparent deliberation over algorithm design choices. This talk illustrates an approach through examples including defining fairness for predictive algorithms, fair policy optimization, and intersectional fairness. While these examples focus on fairness, causal modeling can be applied in similar ways toward achieving other values or objectives in responsible machine learning or data-driven decisions broadly.

Frontpage talks

Statistics

Statistics

15
Feb
Cambridge Statistics Clinic

Statistics

Statistics

Further information

Time:

03Feb
Feb 3rd 2023
14:00 to 15:00

Venue:

MR12, Centre for Mathematical Sciences

Speaker:

Joshua Loftus (London School of Economics)

Series:

Statistics