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

arXiv: https://arxiv.org/abs/2106.13703 · HTML: https://mlsanity.com/paper/2106.13703/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 25 Jun 2021.

## Builds on (most cited first, 30 of 30)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data](https://mlsanity.com/paper/1703.11008/) (2017)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Testing for Outliers with Conformal p-values](https://mlsanity.com/paper/2104.08279/) (2021)
- [Tighter risk certificates for neural networks](https://mlsanity.com/paper/2007.12911/) (2020)
- [Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors](https://mlsanity.com/paper/1712.09376/) (2017)
- [Towards neural networks that provably know when they don't know](https://mlsanity.com/paper/1909.12180/) (2019)
- [Robust Out-of-distribution Detection for Neural Networks](https://mlsanity.com/paper/2003.09711/) (2020)
- [A Strongly Quasiconvex PAC-Bayesian Bound](https://mlsanity.com/paper/1608.05610/) (2016)
- [Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems](https://mlsanity.com/paper/2001.10494/) (2020)
- [A PAC-Bayesian Tutorial with A Dropout Bound](https://mlsanity.com/paper/1307.2118/) (2013)
- [PAC-Bayes with Backprop](https://mlsanity.com/paper/1908.07380/) (2019)
- [Open Category Detection with PAC Guarantees](https://mlsanity.com/paper/1808.00529/) (2018)
- [Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks](https://mlsanity.com/paper/2102.12567/) (2021)
- [PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments](https://mlsanity.com/paper/1806.04225/) (2018)
- [Provably Robust Detection of Out-of-distribution Data (almost) for free](https://mlsanity.com/paper/2106.04260/) (2021)
- [Probably Approximately Correct Vision-Based Planning using Motion Primitives](https://mlsanity.com/paper/2002.12852/) (2020)
- [Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning](https://mlsanity.com/paper/2001.00496/) (2019)
- [RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning](https://mlsanity.com/paper/2104.00543/) (2021)
- [Policy Entropy for Out-of-Distribution Classification](https://mlsanity.com/paper/2005.12069/) (2020)
- [Detecting Rewards Deterioration in Episodic Reinforcement Learning](https://mlsanity.com/paper/2010.11660/) (2020)

## Built on by (most cited first, 4 of 4)

- [Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?](https://mlsanity.com/paper/2605.18045/) (2026)
- [COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP](https://mlsanity.com/paper/2507.22576/) (2025)
- [Deceptive Risk Minimization: Out-of-Distribution Generalization by Deceiving Distribution Shift Detectors](https://mlsanity.com/paper/2509.12081/) (2025)
- [Autonomous Drift Learning in Data Streams: A Unified Perspective](https://mlsanity.com/paper/2605.01295/) (2026)

## Abstract (arXiv)

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. We leverage Probably Approximately Correct (PAC)-Bayes theory to train a policy with a guaranteed bound on performance on the training distribution. Our idea for OOD detection relies on the following intuition: violation of the performance bound on test environments provides evidence that the robot is operating OOD. We formalize this via statistical techniques based on p-values and concentration inequalities. The approach provides guaranteed confidence bounds on OOD detection including bounds on both the false positive and false negative rates of the detector and is task-driven and only sensitive to changes that impact the robot's performance. We demonstrate our approach in simulation and hardware for a grasping task using objects with unfamiliar shapes or poses and a drone performing vision-based obstacle avoidance in environments with wind disturbances and varied obstacle densities. Our examples demonstrate that we can perform task-driven OOD detection within just a handful of trials.