Timezone: »

 
Poster
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation
Shivapratap Gopakumar · Sunil Gupta · Santu Rana · Vu Nguyen · Svetha Venkatesh

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #127
in Thu Poster Session B »

We introduce algorithmic assurance, the problem of testing whether machine learning algorithms are conforming to their intended design goal. We address this problem by proposing an efficient framework for algorithmic testing. To provide assurance, we need to efficiently discover scenarios where an algorithm decision deviates maximally from its intended gold standard. We mathematically formulate this task as an optimisation problem of an expensive, black-box function. We use an active learning approach based on Bayesian optimisation to solve this optimisation problem. We extend this framework to algorithms with vector-valued outputs by making appropriate modification in Bayesian optimisation via the EXP3 algorithm. We theoretically analyse our methods for convergence. Using two real-world applications, we demonstrate the efficiency of our methods. The significance of our problem formulation and initial solutions is that it will serve as the foundation in assuring humans about machines making complex decisions.

Keywords: Active Learning · Gaussian Processes · Predictive Models · Classification · Regression · Bayesian Theory
[ Paper] 

Author Information

Shivapratap Gopakumar (Deakin University)
Sunil Gupta (Deakin University)
Santu Rana (Deakin University)
Vu Nguyen (Deakin University)
Svetha Venkatesh (Deakin University)

More from the Same Authors