Robust Allocations with Diversity Constraint
Dec 6, 2021
Speakers
Lodewijk Gelauff
Speaker · 0 followers
Ashish Goel
Speaker · 0 followers
Aleksandra Korolova
Speaker · 0 followers
Kamesh Munagala
Speaker · 0 followers
About
We consider the problem of allocating divisible items among multiple agents, and consider the setting where any agent is allowed to introduce diversity constraints on the items they are allocated. We motivate this via settings where the items themselves correspond to user ad slots or task workers with attributes such as race and gender on which the principal seeks to achieve demographic parity. We consider the following question: When an agent expresses diversity constraints into an allocation rule, is the allocation of other agents hurt significantly? If this happens, the cost of introducing such constraints is disproportionately borne by agents who do not benefit from diversity. We codify this via two desiderata capturing robustness. These are no negative externality – other agents are not hurt – and monotonicity – the agent enforcing the constraint does not see a large increase in value. We show in a formal sense that the Nash Welfare rule that maximizes product of agent values is uniquely positioned to be robust when diversity constraints are introduced, while almost all other natural allocation rules fail this criterion. We also show that the guarantees achieved by Nash Welfare are nearly optimal within a widely studied class of allocation rules. We finally perform an empirical simulation on real-world data that models ad allocations to show that this gap between Nash Welfare and other rules persists in the wild.We consider the problem of allocating divisible items among multiple agents, and consider the setting where any agent is allowed to introduce diversity constraints on the items they are allocated. We motivate this via settings where the items themselves correspond to user ad slots or task workers with attributes such as race and gender on which the principal seeks to achieve demographic parity. We consider the following question: When an agent expresses diversity constraints into an allocation r…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Introduction: Are All Neurons Created Equal? Interpreting and Controlling BERT through Individual Neurons
Watch later
Omer Antverg, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep-SWIM: A few-shot learning approach to classify Solar WInd Magnetic field structures
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Rapid Data Development Platform for Long Tail Vision Applications
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks
Watch later
Chen Ma, …
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%
On the Expressivity of Markov Reward
Watch later
Dave Abel, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Differentiable rendering with perturbed optimizers
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%