# Instances of Computational Optimal Recovery: Dealing with Observation Errors

arXiv: https://arxiv.org/abs/2004.00192 · HTML: https://mlsanity.com/paper/2004.00192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 1 of 1)

- [Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter?](https://mlsanity.com/paper/2111.02601/) (2021)

## Abstract (arXiv)

When attempting to recover functions from observational data, one naturally seeks to do so in an optimal manner with respect to some modeling assumption. With a focus put on the worst-case setting, this is the standard goal of Optimal Recovery. The distinctive twists here are the consideration of inaccurate data through some boundedness models and the emphasis on computational realizability. Several scenarios are unraveled through the efficient constructions of optimal recovery maps: local optimality under linearly or semidefinitely describable models, global optimality for the estimation of linear functionals under approximability models, and global near-optimality under approximability models in the space of continuous functions.