Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability

by   Gintare Karolina Dziugaite, et al.

To date, there has been no formal study of the statistical cost of interpretability in machine learning. As such, the discourse around potential trade-offs is often informal and misconceptions abound. In this work, we aim to initiate a formal study of these trade-offs. A seemingly insurmountable roadblock is the lack of any agreed upon definition of interpretability. Instead, we propose a shift in perspective. Rather than attempt to define interpretability, we propose to model the act of enforcing interpretability. As a starting point, we focus on the setting of empirical risk minimization for binary classification, and view interpretability as a constraint placed on learning. That is, we assume we are given a subset of hypothesis that are deemed to be interpretable, possibly depending on the data distribution and other aspects of the context. We then model the act of enforcing interpretability as that of performing empirical risk minimization over the set of interpretable hypotheses. This model allows us to reason about the statistical implications of enforcing interpretability, using known results in statistical learning theory. Focusing on accuracy, we perform a case analysis, explaining why one may or may not observe a trade-off between accuracy and interpretability when the restriction to interpretable classifiers does or does not come at the cost of some excess statistical risk. We close with some worked examples and some open problems, which we hope will spur further theoretical development around the tradeoffs involved in interpretability.



There are no comments yet.


page 1

page 2

page 3

page 4


Trade-offs in the Design of Multimodal Interaction for Older Adults

This paper presents key aspects and trade-offs that designers and Human-...

Model Learning with Personalized Interpretability Estimation (ML-PIE)

High-stakes applications require AI-generated models to be interpretable...

Learning a Formula of Interpretability to Learn Interpretable Formulas

Many risk-sensitive applications require Machine Learning (ML) models to...

A Formal Framework to Characterize Interpretability of Procedures

We provide a novel notion of what it means to be interpretable, looking ...

The Limits of Computation in Solving Equity Trade-Offs in Machine Learning and Justice System Risk Assessment

This paper explores how different ideas of racial equity in machine lear...

Makespan Trade-offs for Visiting Triangle Edges

We study a primitive vehicle routing-type problem in which a fleet of nu...

Trade-offs in Top-k Classification Accuracies on Losses for Deep Learning

This paper presents an experimental analysis about trade-offs in top-k c...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.