# Bayesian Optimization Meets Laplace Approximation for Robotic Introspection

arXiv: https://arxiv.org/abs/2010.16141 · HTML: https://mlsanity.com/paper/2010.16141/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Explaining Bayesian Neural Networks](https://mlsanity.com/paper/2108.10346/) (2021)
- [Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes](https://mlsanity.com/paper/2109.09690/) (2021)
- [Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks](https://mlsanity.com/paper/2307.07753/) (2023)
- [Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities](https://mlsanity.com/paper/2210.09678/) (2022)

## Abstract (arXiv)

In robotics, deep learning (DL) methods are used more and more widely, but their general inability to provide reliable confidence estimates will ultimately lead to fragile and unreliable systems. This impedes the potential deployments of DL methods for long-term autonomy. Therefore, in this paper we introduce a scalable Laplace Approximation (LA) technique to make Deep Neural Networks (DNNs) more introspective, i.e. to enable them to provide accurate assessments of their failure probability for unseen test data. In particular, we propose a novel Bayesian Optimization (BO) algorithm to mitigate their tendency of under-fitting the true weight posterior, so that both the calibration and the accuracy of the predictions can be simultaneously optimized. We demonstrate empirically that the proposed BO approach requires fewer iterations for this when compared to random search, and we show that the proposed framework can be scaled up to large datasets and architectures.