Nov 16, 2023 · To address this issue, we propose asymptotically fair participation as a condition to maintain long-term model performance over all demographic ...

This approach provides a theoretical framework that reinterprets deep learning methodologies through optimal control (Liu and Theodorou, 2019) . The ...

Bibliographic details on Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective.

Modeling Opt.(NEMO), 1, 2019. 2, 2019. Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective. Z Chen, Q Li, Z Zhang.

Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective ... control variables are considered as the model parameters ...

The performance of state-of-the-art machine learn- ing models is observed to degrade in scenarios involving under-represented demographic popu-.

Aug 19, 2023 · ""Modern control theory, especially the branch known as stochastic optimal control, has as its goal the design of systems that maximize an ...

... theory. Being an empirical science does not mean that the field is a "wild west". Deep learning models are subjectable to repeatable controlled experiments ...

We study the problem of distribution shift generally arising in machine-learning augmented hybrid simulation, where parts of simulation algorithms are replaced ...

We show this design guarantees fairness in terms of the asymptotic convergence behaviors of the models of the nodes instead of localized to certain iteration ...