QuantifyML: How Good is my Machine Learning Model?
Open Access
- 21 October 2021
- journal article
- Published by Open Publishing Association in Electronic Proceedings in Theoretical Computer Science
- Vol. 348, 92-100
- https://doi.org/10.4204/eptcs.348.6
Abstract
The efficacy of machine learning models is typically determined by computing their accuracy on test data sets. However, this may often be misleading, since the test data may not be representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. Given a trained model, QuantifyML translates it into a C program and feeds it to the CBMC model checker to produce a formula in Conjunctive Normal Form (CNF). The formula is analyzed with off-the-shelf model counters to obtain precise counts with respect to different model behavior. QuantifyML enables i) evaluating learnability by comparing the counts for the outputs to ground truth, expressed as logical predicates, ii) comparing the performance of models built with different machine learning algorithms (decision-trees vs. neural networks), and iii) quantifying the safety and robustness of models.This publication has 23 references indexed in Scilit:
- The Limitations of Deep Learning in Adversarial SettingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- $$\#\exists $$ SAT: Projected Model CountingPublished by Springer Science and Business Media LLC ,2015
- CBMC – C Bounded Model CheckerLecture Notes in Computer Science, 2014
- A Scalable Approximate Model CounterLecture Notes in Computer Science, 2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- A Tool for Checking ANSI-C ProgramsLecture Notes in Computer Science, 2004
- Bounded Model CheckingPublished by Elsevier BV ,2003
- AlloyACM Transactions on Software Engineering and Methodology, 2002
- Exploring Very Large State Spaces Using Genetic AlgorithmsLecture Notes in Computer Science, 2002
- A survey of decision tree classifier methodologyIEEE Transactions on Systems, Man, and Cybernetics, 1991