Generalized Riesz Regression: A Unified Framework for Debiased Machine Learning with Riesz Representer Fitting under Bregman Divergence
Read the original on arXiv Machine Learning →The paper introduces generalized Riesz regression, a framework that minimizes a Bregman divergence made observable through the Riesz identity. By selecting squared or Kullback–Leibler-type divergences, it recovers existing Riesz regression, tailored loss minimization, and density‑ratio objectives. The authors derive first‑order conditions that enforce empirical Riesz equations in model‑dependent tangent directions, provide convergence rates for sparse, RKHS, and neural network models, and establish asymptotic normality under Donsker or cross‑fitting conditions, with applications to treatment effects, average marginal effects, and covariate shift.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.