Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning

1 code implementation • 25 Jun 2021 • Alec Farid, Sushant Veer, Divyanshu Pachisia, Anirudha Majumdar

Our goal is to perform out-of-distribution (OOD) detection, i. e., to detect when a robot is operating in environments drawn from a different distribution than the ones used to train the robot.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability

1 code implementation • NeurIPS 2021 • Alec Farid, Anirudha Majumdar

We are motivated by the problem of providing strong generalization guarantees in the context of meta-learning.

Generalization Bounds Meta-Learning

PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments

1 code implementation • 11 Jun 2018 • Anirudha Majumdar, Alec Farid, Anoopkumar Sonar

The key technical idea behind our approach is to leverage tools from generalization theory in machine learning by exploiting a precise analogy (which we present in the form of a reduction) between generalization of control policies to novel environments and generalization of hypotheses in the supervised learning setting.