Inverse classification with logistic and softmax classifiers: efficient optimization
Carreira-Perpiñán, Miguel Á., Hada, Suryabhan Singh
In recent years, a certain type of problems have become of interest where one wants to query a trained classifier. Specifically, one wants to find the closest instance to a given input instance such that the classifier's predicted label is changed in a desired way. Examples of these ``inverse classification'' problems are counterfactual explanations, adversarial examples and model inversion. All of them are fundamentally optimization problems over the input instance vector involving a fixed classifier, and it is of interest to achieve a fast solution for interactive or real-time applications. We focus on solving this problem efficiently for two of the most widely used classifiers: logistic regression and softmax classifiers. Owing to special properties of these models, we show that the optimization can be solved in closed form for logistic regression, and iteratively but extremely fast for the softmax classifier. This allows us to solve either case exactly (to nearly machine precision) in a runtime of milliseconds to around a second even for very high-dimensional instances and many classes.
Sep-16-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- District of Columbia > Washington (0.04)
- New York > New York County
- New York City (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Florida > Miami-Dade County
- Miami (0.04)
- California
- San Diego County > San Diego (0.04)
- Merced County > Merced (0.04)
- Canada > Alberta
- United States
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- Switzerland > Zürich
- Zürich (0.14)
- Spain > Basque Country
- Biscay Province > Bilbao (0.04)
- Iceland > Capital Region
- Reykjavik (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- United Kingdom > England
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.69)
- Industry:
- Information Technology (0.46)
- Technology: