Multigroup Robustness
To address the shortcomings of real-world datasets, robust learning algorithms have been designed to overcome arbitrary and indiscriminate data corruption. However, practical processes of gathering data may lead to patterns of data corruption that are localized to specific partitions of the training dataset. Motivated by critical applications where the learned model is deployed to make predictions about people from a rich collection of overlapping subpopulations, we initiate the study of multigroup robust algorithms whose robustness guarantees for each subpopulation only degrade with the amount of data corruption inside that subpopulation. When the data corruption is not distributed uniformly over subpopulations, our algorithms provide more meaningful robustness guarantees than standard guarantees that are oblivious to how the data corruption and the affected subpopulations are related. Our techniques establish a new connection between multigroup fairness and robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Rate-Splitting Multiple Access for Multigroup Multicast and Multibeam Satellite Systems
This work focuses on the promising Rate-Splitting Multiple Access (RSMA) and its beamforming design problem to achieve max-min fairness (MMF) among multiple co-channel multicast groups with imperfect channel state inform…
FairnessManagementMultigroup Multicast Design for Pinching-Antenna Systems: Waveguide-Division or Waveguide-Multiplexing?
This article addresses the design of multigroup multicast communications in the pinching-antenna system (PASS). A PASS-enabled multigroup transmission framework is proposed to maximize multicast rates under a couple of t…
Near-Optimal Cell-Free Beamforming for Physical Layer Multigroup Multicasting
Physical layer multicasting is an efficient transmission technique that exploits the beamforming potential at the transmitting nodes and the broadcast nature of the wireless channel, together with the demand for the same…
Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture
The validation of advanced nuclear reactor designs and fuel concepts requires critical experiments with high neutronic similarity to the target technology. Neutronic similarity is quantified by the correlation coefficien…
Power Control for Multigroup Multicast Cell-Free Massive MIMO Downlink
We consider a multigroup multicast cell-free multiple-input multiple-output (MIMO) downlink system with short-term power constraints. In particular, the normalized conjugate beamforming scheme is adopted at each access p…
Fairness