Timezone: »

Gradient-Based Monitoring of Learning Machines
Lang Liu

Fri Jul 17 07:30 AM -- 07:40 AM (PDT) @ None
Event URL: https://slideslive.com/38931677/gradientbased-monitoring-of-learning-machines?ref=account-folder-55868-folders »

The widespread use of machine learning algorithms calls for automatic change detection algorithms to monitor their behaviour over time. As a machine learning algorithm learns from a continuous, possibly evolving, stream of data, it is desirable and often critical to supplement it with a companion change detection algorithm to facilitate its monitoring and control. We present a generic score-based change detection method that can detect a change in any number of (hidden) components of a machine learning model trained via empirical risk minimization. This proposed statistical hypothesis test can be readily implemented for such models designed within a differentiable programming framework. We establish the consistency of the hypothesis test and show how to calibrate it based on our theoretical results. We illustrate the versatility of the approach on synthetic and real data.

Author Information

Lang Liu (University of Washington)

More from the Same Authors

  • 2020 : Poster session »
    Janis Klaise · Lang Liu · Begum Taskazan · Lasse F. Wolff Anthony · Clive Cox · Omid Aramoon · Ting-wu Chin · Alexander Lavin