mlsanityData to 7 Oct 2026

An Interpretable Neural Network for Parameter Inference

arXiv 2106.05536 ↗First posted 10 Jun 2021stat.ML cs.LG econ.EMcited by 0

Not on the map. Why?

Abstract (arXiv)

Adoption of deep neural networks in fields such as economics or finance has been constrained by the lack of interpretability of model outcomes. This paper proposes a generative neural network architecture - the parameter encoder neural network (PENN) - capable of estimating local posterior distributions for the parameters of a regression model. The parameters fully explain predictions in terms of the inputs and permit visualization, interpretation and inference in the presence of complex heterogeneous effects and feature dependencies. The use of Bayesian inference techniques offers an intuitive mechanism to regularize local parameter estimates towards a stable solution, and to reduce noise-fitting in settings of limited data availability. The proposed neural network is particularly well-suited to applications in economics and finance, where parameter inference plays an important role. An application to an asset pricing problem demonstrates how the PENN can be used to explore nonlinear risk dynamics in financial markets, and to compare empirical nonlinear effects to behavior posited by financial theory.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 82 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

28 of 82 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
  8. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  9. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  10. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  11. 2018On the Robustness of Interpretability Methodscited by 310
  12. 2016Generalized Random Forestscited by 309
16 more
  1. 2017Advances in Variational Inferencecited by 236
  2. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  3. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 99
  4. 2018Deep Neural Networks for Estimation and Inferencecited by 62
  5. 2019Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causalitycited by 55
  6. 2016Approximate Residual Balancing: De-Biased Inference of Average Treatment Effects in High Dimensionscited by 50
  7. 2019Scaleable input gradient regularization for adversarial robustnesscited by 45
  8. 2021Interpretable Models for Granger Causality Using Self-explaining Neural Networkscited by 44
  9. 2013Robust Inference on Average Treatment Effects with Possibly More Covariates than Observationscited by 38
  10. 2013Program Evaluation and Causal Inference with High-Dimensional Datacited by 29
  11. 2018Local Linear Forestscited by 19
  12. 2019Significance Tests for Neural Networkscited by 17
  13. 2020Discovering Nonlinear Relations with Minimum Predictive Information Regularizationcited by 16
  14. 2017Symmetric Variational Autoencoder and Connections to Adversarial Learningcited by 14
  15. 2017An Interpretable and Sparse Neural Network Model for Nonlinear Granger Causality Discoverycited by 5
  16. 2019From interpretability to inference: an estimation framework for universal approximatorscited by 3

Built on by

Not cited yet.