algebra is the study of…

• symbols/variables
• transformations/operations: “add”, “multiply”
• simple functions
• abstraction
• substitution

The algebreic multiplicity for a given eigenvalue is the multiplicity for which the linear factor containing it shows up in the characteristic polynomial.

Could algorithms make more equitable decisions? No: algorithms may propagate and amplify biases—its not enough just to learn/optimize.

Collaboration with other fields has both a language gap and a value gap.

Technical Algorithmic Fairness

fair scheduling, distributed computing, envy-freeness, cake cutting, stable matching, etc.

Interpreting Individual Probabilities

“I have n% probability of developing this thing” — what does this mean? what does it capture in the environment?

Applications

• insurance: how does actuarial scenarios work for this case—it is, in those cases, context dependent
• satisfying fairness maybe mis-generalized: discrimination can be subtle for a given measure (do you know it when you see it?)

Definitions of fairness, however, is important to characterize a system.

• Startups

Kwotes

“Working with big tech is a job closer to big tech.”