# Hyperparameter Analysis for Derivative Compressive Sampling

arXiv: https://arxiv.org/abs/2108.04355 · HTML: https://mlsanity.com/paper/2108.04355/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 24 references that are in the map.
- First posted on arXiv 5 Aug 2021.

## Builds on (most cited first, 3 of 3)

- [Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer](https://mlsanity.com/paper/1710.03850/) (2017)
- [Joint Dictionaries for Zero-Shot Learning](https://mlsanity.com/paper/1709.03688/) (2017)
- [Testing fine-grained parallelism for the ADMM on a factor-graph](https://mlsanity.com/paper/1603.02526/) (2016)

## Abstract (arXiv)

Derivative compressive sampling (DCS) is a signal reconstruction method from measurements of the spatial gradient with sub-Nyquist sampling rate. Applications of DCS include optical image reconstruction, photometric stereo, and shape-from-shading. In this work, we study the sensitivity of DCS with respect to algorithmic hyperparameters using a brute-force search algorithm. We perform experiments on a dataset of surface images and deduce guidelines for the user to setup values for the hyperparameters for improved signal recovery performance.