arXiv Machine Learning By Shizhou Xu

Separation-Utility Pareto Frontier: An Information-Theoretic Characterization

Read the original on arXiv Machine Learning →

arXiv:2602. 04408v3 Announce Type: replace Abstract: We study the Pareto frontier (optimal trade-off) between utility and separation, a fairness criterion requiring predictive independence from sensitive attributes conditional on the true outcome.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 7

Machine Unlearning via Information Theoretic Regularization

arXiv:2502. 05684v5 Announce Type: replace-cross Abstract: How can we effectively remove or ``unlearn'' undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees?

By Shizhou Xu, Thomas Strohmer
arXiv Machine Learning
Jul 7

Functional Bilevel Optimization for Predictive Fairness

arXiv:2607. 05098v1 Announce Type: new Abstract: When sensitive attributes are continuous and high-dimensional $-$ demographic score vectors, posteriors over attributes, age or income profiles $-$ enforcing full statistical independence is often too restrictive, and existing relaxations rely on indirect dependence penalties or adversarial schemes that do not directly target the fairness-accuracy trade-off.

By Ieva Petrulionyte, Julien Mairal, Michael Arbel
arXiv AI
Jun 2

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning

arXiv:2606. 02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data.

By Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim, Zhengyuan Liu, Nancy F. Chen, Bryan Kian Hsiang Low