References

The papers behind the package, grouped by role, each with a one-line note on why it matters here. The links go to the transcribed markdown in the repository.

Core framework

  • Farrell, Liang, Misra (2021), “Deep Neural Networks for Estimation and Inference”, Econometrica. transcript. The foundational result: neural-network plug-ins are biased, the influence-function correction restores valid inference.

  • Farrell, Liang, Misra (2025), “Deep Learning for Individual Heterogeneity”, working paper. transcript. The extended theory this package follows for the structural-parameter setup.

Applications

  • Dubé, Misra (2023), “Personalized Pricing and Consumer Welfare”, Journal of Political Economy. transcript. Heterogeneous price elasticity and the welfare targets (elasticity, profit, consumer surplus).

  • Hetzenecker, Osterhaus (2024), “Deep Learning for Heterogeneous Parameters in Discrete Choice Models”, arXiv 2408.09560. transcript. The multinomial-logit (conditional logit) setup.

  • Colangelo, Lee (2026), “Double Debiased Machine Learning Nonparametric Inference with Continuous Treatments”, JBES. transcript. Continuous-treatment dose-response.

  • Chen, Liu, Ma, Zhang (2024), “Causal Inference of General Treatment Effects using Neural Networks”, Journal of Econometrics. transcript.

  • Ye et al. (2025), “Deep-Learning-Based Causal Inference for Large-Scale Combinatorial Experiments”, Management Science. transcript. The combinatorial multi-treatment model.

Automatic debiasing and Riesz representation

  • Chernozhukov, Newey, Quintas-Martinez, Syrgkanis (2022), “RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests”, ICML. transcript. The basis for the RieszNet procedure.

  • Chernozhukov, Newey, Singh, Syrgkanis (2022), “Automatic Debiased Machine Learning of Causal and Structural Effects”, Econometrica. transcript.

  • Chernozhukov, Newey, Quintas-Martinez, Syrgkanis (2021), “Automatic Debiased ML via Neural Nets for Generalized Linear Regression”, working paper. transcript.

  • Hines, Hines (2025), “Automatic Debiasing of Neural Networks via Moment-Constrained Learning”, CLeaR. transcript.

DNN architecture and influence functions

  • Shi, Blei, Veitch (2019), “Adapting Neural Networks for the Estimation of Treatment Effects (DragonNet)”, NeurIPS. transcript.

  • Li, McCoy et al. (2025), “Targeted Deep Architectures for Estimation and Inference”, arXiv 2507.12435. transcript.

  • Shirakawa et al. (2024), “Deep Longitudinal Targeted Minimum Loss-based Estimation”, ICML. transcript.

  • Liu et al. (2024), “DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation”, ICML. transcript.

  • Cai, Fonseca, Hou, Namkoong (2025), “C-Learner: Constrained Learning for Causal Inference and Semiparametric Statistics”, arXiv 2405.09493. transcript.

Theory

  • Yan, Chen, Yao (2025), “Overparameterized Neural Networks in Semiparametric Inference”, arXiv 2504.19089. transcript.

  • Metzger (2022), “Adversarial Estimators”, arXiv 2204.10495. transcript.

  • Foster, Syrgkanis (2023), “Orthogonal Statistical Learning”, Annals of Statistics. transcript.

Frontier

  • Melnychuk, Feuerriegel (2026), “GDR-Learners: Generalized Doubly Robust Learners for Causal Inference”, ICLR. transcript.

  • Nguyen (2025), “Neural Network Estimation and Simulation for Dynamic Discrete Choice Models”, Georgetown JMP. transcript.