On agnostic boosting and parity learning

By Adam Tauman Kalai, Yishay Mansour, Elad Verbin. 2008

70 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (2017, background): “As we show in the full version, auditing of a given class is closely related to weak agnostic learning (Kearns et al., 1994; Kalai et al., 2008) of that same class.”
Calibration for the (Computationally-Identifiable) Masses (2017, methodology): “In the case where p ∗ is arbitrary, we show that improving the dependence on |C| is possible if C is structured in a certain way, drawing a connection to the literature on agnostic learning [Hau92, KSS94,KMV08,Fel10].”
Multiaccuracy: Black-Box Post-Processing for Fairness in Classification (2018, background): “Both works [13, 16] connect the task of learning a model that satisfies the notion of fairness to the task of (weak) agnostic learning [9, 14, 15, 17].”
When optimizing nonlinear objectives is no harder than linear objectives (2018, methodology): “The general approach of reducing optimization to linear optimization has been utilized in many areas of machine learning (Jaggi, 2013; Kalai et al., 2008).”
Unleashing Linear Optimizers for Group-Fair Learning and Optimization (2018, methodology): “The general approach of reducing optimization to linear optimization has been utilized in many areas of machine learning (Jaggi, 2013; Kalai et al., 2008).”
Multicalibration: Calibration for the (Computationally-Identifiable) Masses (2018, methodology): “exactly the requirement for a weak agnostic learner, as defined in (Kalai et al., 2008; Feldman, 2010).”