1 citations · 1 across the 2 of their papers we have counts for
3 papers
stat.ML2022
Classification as Direction Recovery: Improved Guarantees via Scale Invariance
Suhas Vijaykumar, Claire Lazar Reich
Modern algorithms for binary classification rely on an intermediate regression problem for computational tractability. In this paper, we establish a geometric distinction between c…
stat.ML2021★ 1 cited
Affirmative Action vs. Affirmative Information
Claire Lazar Reich
Critical decisions in hiring, college admissions, and credit lending are guided by predictions made in the presence of uncertainty. While uncertainty imparts errors across all demo…
cs.LG2020
A Possibility in Algorithmic Fairness: Can Calibration and Equal Error Rates Be Reconciled?
Claire Lazar Reich, Suhas Vijaykumar
Decision makers increasingly rely on algorithmic risk scores to determine access to binary treatments including bail, loans, and medical interventions. In these settings, we reconc…