On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

11/02/2022
by   Dennis Wei, et al.
0

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing safety, we introduce the concept of maximum deviation via an optimization problem to find the largest deviation of a supervised learning model from a reference model regarded as safe. We then show how interpretability facilitates this safety assessment. For models including decision trees, generalized linear and additive models, the maximum deviation can be computed exactly and efficiently. For tree ensembles, which are not regarded as interpretable, discrete optimization techniques can still provide informative bounds. For a broader class of piecewise Lipschitz functions, we leverage the multi-armed bandit literature to show that interpretability produces tighter (regret) bounds on the maximum deviation. We present case studies, including one on mortgage approval, to illustrate our methods and the insights about models that may be obtained from deviation maximization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2019

Making Bayesian Predictive Models Interpretable: A Decision Theoretic Approach

A salient approach to interpretable machine learning is to restrict mode...
research
02/09/2019

Assessing the Local Interpretability of Machine Learning Models

The increasing adoption of machine learning tools has led to calls for a...
research
03/20/2021

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges

Interpretability in machine learning (ML) is crucial for high stakes dec...
research
02/17/2015

Regret bounds for Narendra-Shapiro bandit algorithms

Narendra-Shapiro (NS) algorithms are bandit-type algorithms that have be...
research
05/10/2019

Formal Verification of Input-Output Mappings of Tree Ensembles

Recent advances in machine learning and artificial intelligence are now ...
research
04/12/2019

Boosting insights in insurance tariff plans with tree-based machine learning

Pricing actuaries typically stay within the framework of generalized lin...

Please sign up or login with your details

Forgot password? Click here to reset