mlsanityData to 13 Oct 2026

Outcome Assumptions and Duality Theory for Balancing Weights

arXiv 2203.09557 ↗First posted 17 Mar 2022stat.ME cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

We study balancing weight estimators, which reweight outcomes from a source population to estimate missing outcomes in a target population. These estimators minimize the worst-case error by making an assumption about the outcome model. In this paper, we show that this outcome assumption has two immediate implications. First, we can replace the minimax optimization problem for balancing weights with a simple convex loss over the assumed outcome function class. Second, we can replace the commonly-made overlap assumption with a more appropriate quantitative measure, the minimum worst-case bias. Finally, we show conditions under which the weights remain robust when our assumptions on the outcomes are wrong.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

20 of 50 references.

References · 20

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,030
  2. 2020Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effectscited by 72
  3. 2016Approximate Residual Balancing: De-Biased Inference of Average Treatment Effects in High Dimensionscited by 50
  4. 2020Counterfactual Representation Learning with Balancing Weightscited by 45
  5. 2018DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Trainingcited by 42
  6. 2016Generalized Optimal Matching Methods for Causal Inferencecited by 39
  7. 2019Generalized Resilience and Robust Statisticscited by 37
  8. 2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
  9. 2016Covariate Balancing Propensity Score by Tailored Loss Functionscited by 34
  10. 2020Optimal Bounds between f-Divergences and Integral Probability Metricscited by 27
  11. 2019Bridging the Gap Between f-GANs and Wasserstein GANscited by 23
  12. 2021The Balancing Act in Causal Inferencecited by 20
8 more
  1. 2017Minimal Dispersion Approximately Balancing Weights: Asymptotic Properties and Practical Considerationscited by 18
  2. 2017Regularized calibrated estimation of propensity scores with model misspecification and high-dimensional datacited by 15
  3. 2020Optimizing Variational Representations of Divergences and Accelerating their Statistical Estimationcited by 15
  4. 2019Permutation Weightingcited by 14
  5. 2015Entropy balancing is doubly robustcited by 13
  6. 2019Minimax Linear Estimation of the Retargeted Meancited by 11
  7. 2019Formulation and properties of a divergence used to compare probability measures without absolute continuitycited by 11
  8. 2018Adversarial Balancing for Causal Inferencecited by 10

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2023Augmented balancing weights as linear regressioncited by 21
  2. 2022Generalized Balancing Weights via Deep Neural Networkscited by 1
  3. 2024Towards Representation Learning for Weighting Problems in Design-Based Causal Inferencecited by 1
  4. 2026Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inferencecited by 1
  5. 2025Learning density ratios in causal inference using Bregman-Riesz regressioncited by 0