Fairness without Regret

07/11/2019
by   Marcus Hutter, et al.
7

A popular approach of achieving fairness in optimization problems is by constraining the solution space to "fair" solutions, which unfortunately typically reduces solution quality. In practice, the ultimate goal is often an aggregate of sub-goals without a unique or best way of combining them or which is otherwise only partially known. I turn this problem into a feature and suggest to use a parametrized objective and vary the parameters within reasonable ranges to get a "set" of optimal solutions, which can then be optimized using secondary criteria such as fairness without compromising the primary objective, i.e. without regret (societal cost).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/23/2019

Achieving Fairness in the Stochastic Multi-armed Bandit Problem

We study an interesting variant of the stochastic multi-armed bandit pro...
research
04/26/2022

Bandwidth Allocation Games

Internet providers often offer data plans that, for each user's monthly ...
research
04/21/2023

Optimizing fairness tradeoffs in machine learning with multiobjective meta-models

Improving the fairness of machine learning models is a nuanced task that...
research
02/25/2023

Improving Fairness in Information Exposure by Adding Links

Fairness in influence maximization has been a very active research topic...
research
01/23/2018

An Efficient Primal-Dual Algorithm for Fair Combinatorial Optimization Problems

We consider a general class of combinatorial optimization problems inclu...
research
08/11/2022

Enabling Long-term Fairness in Dynamic Resource Allocation

We study the fairness of dynamic resource allocation problem under the α...
research
02/16/2022

Fairness constraint in Structural Econometrics and Application to fair estimation using Instrumental Variables

A supervised machine learning algorithm determines a model from a learni...

Please sign up or login with your details

Forgot password? Click here to reset