Deep Learning Diagnostics ‒ How to Avoid Being Fooled by TensorFlow, PyTorch, or MXNet with the Help of Modern Econometrics

Schriftenreihe des Instituts für Empirie & Statistik der FOM Hochschule, Band 24 (2021)

60 Pages Posted: 1 Apr 2021

See all articles by Frank Lehrbass

Frank Lehrbass

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting); FOM University of Applied Sciences for Economics and Management; University of the Bundesbank

Date Written: March 12, 2021

Abstract

Training a Multi-Layer Perceptron (MLP) to achieve a minimum level of MSE is akin to doing Non-Linear Regression (NLR). Therefore, we use available econometric theory and the corresponding tools in R. Only if certain assumptions about the error term in the Data Generating Process are in place, may we enjoy the trained MLP as a consistent estimator. To verify the assumptions, careful diagnostics are necessary.

Using controlled experiments we show that even in an ideal setting, an MLP may fail to learn a relationship whereas NLR performs better. We illustrate how the MLP is outperformed by Non-Linear Quantile Regression in the presence of outliers. A third situation in which the MLP is often led astray is where there is no relationship and the MLP still learns a relationship producing high levels of R². We show that circumventing the trap of spurious learning is only possible with the help of diagnostics.

Keywords: Non-Linear Regression, MLP, spurious regression, spurious learning

JEL Classification: C01, C02, C19, C55

Suggested Citation

Lehrbass, Frank and Lehrbass, Frank, Deep Learning Diagnostics ‒ How to Avoid Being Fooled by TensorFlow, PyTorch, or MXNet with the Help of Modern Econometrics (March 12, 2021). Schriftenreihe des Instituts für Empirie & Statistik der FOM Hochschule, Band 24 (2021), Available at SSRN: https://ssrn.com/abstract=3803328

Frank Lehrbass (Contact Author)

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting) ( email )

Dusseldorf
Germany

HOME PAGE: http://lehrbass.de

FOM University of Applied Sciences for Economics and Management ( email )

Toulouser Allee 53
Dusseldorf, 40476
Germany

University of the Bundesbank ( email )

Schloss
Hachenburg, 57627
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
102
Abstract Views
449
Rank
510,657
PlumX Metrics