Machine learning algorithms increasingly influence our lives, making fairness critical to prevent discrimination based on gender, ethnicity, or other factors. In this talk I am going to focus on two important topics in algorithmic fairness; what is a fair algorithm, and how to achieve notions of fairness.
There is no universal definition of a fair algorithm that applies in all situations. Instead, there are many different definitions, often contradictory, and the choice of the right definition for each setting is a complex policy question. In this talk I am going to expand on the importance of fairness definitions and talk about an ad auction setting for job ads, where there is more than a single fairness definition. I am going to show how changing the definition can have advantages in reaching the desired outcome.
Regarding the question of how to achieve fairness, I am going to talk about omnipredictors with fairness constraints. An omnipredictor is a predictor that can be efficiently post-processed to minimize many different loss functions. I am going to discuss my work that extends the notion of an omnipredictor to optimization problems with constraints. If the constraints or the loss are changed, then only the efficient post-processing needs to be changed. Since fairness constraints are a result of a policy, it is rather likely that they might change over time. This works allows handling changing fairness constraints efficiently.
Additionally, I'll touch on how algorithmic fairness principles apply beyond their usual scope, in complexity theory. I'll also briefly discuss a work on quantum error correction. Concluding the talk, I'll share my research interests and future directions.
Inbal Livni Navon is a postdoctoral researcher at Stanford University, working with Prof. Omer Reingold. She received her Ph.D. in 2021 from the Weizmann Institute of Science where she was advised by Prof. Irit Dinur. She is interested in Algorithmic fairness, in studying different fairness definitions and in fair algorithms. She is also interested in expander graphs and expander-based error correcting codes.