Nov 28, 2022
Speaker · 0 followers
Speaker · 2 followers
Speaker · 1 follower
Predictive models often include group attributes that encode personal characteristics like sex, blood type, or HIV status. Personalized models must ensure fair use – i.e., groups who provide personal data should expect to receive a tailored improvement in accuracy compared to a non-personalized model. In this paper, we derive conditions under which one can detect fair use violations in predictive models and characterize when estimating fair use is impossible. We propose a metric to evaluate the worst-case accuracy gain across groups called the benefit of personalization (BoP). We obtain bounds on the error probability for testing if the BoP is above a target threshold given finite samples. Remarkably, our bounds provide an information-theoretic limit on the number of group attributes that a model can use to allow for verification – beyond this limit, it is impossible to reliably detect if personalization harms or benefits all groups. We also derive statistical limits for the minimax mean-square error of estimating the BoP. Our results show that there is no way to reliably determine if a personalized model with k ≥ 19 attributes benefits every group that provides personal data, even when we are given a dataset with N = 8×10^9 samples (i.e., one observation for each person in the world).Predictive models often include group attributes that encode personal characteristics like sex, blood type, or HIV status. Personalized models must ensure fair use – i.e., groups who provide personal data should expect to receive a tailored improvement in accuracy compared to a non-personalized model. In this paper, we derive conditions under which one can detect fair use violations in predictive models and characterize when estimating fair use is impossible. We propose a metric to evaluate the…
Account · 952 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Andy Zeng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Quan Vuong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
William Wong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Ganchao Wei, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Wei Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Dandan Guo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%