# Info-Greedy sequential adaptive compressed sensing

arXiv: https://arxiv.org/abs/1407.0731 · HTML: https://mlsanity.com/paper/1407.0731/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2014.

## Built on by (most cited first, 9 of 9)

- [Active Diffusion Subsampling](https://mlsanity.com/paper/2406.14388/) (2024)
- [Active inference and deep generative modeling for cognitive ultrasound](https://mlsanity.com/paper/2410.13310/) (2024)
- [Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domains](https://mlsanity.com/paper/2108.07399/) (2021)
- [RL-NCS: Reinforcement learning based data-driven approach for nonuniform compressed sensing](https://mlsanity.com/paper/2107.00838/) (2021)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems](https://mlsanity.com/paper/2407.07794/) (2024)
- [Cost-Aware Diffusion Active Search](https://mlsanity.com/paper/2602.19538/) (2026)
- [Classification-oriented adaptive sensing via posterior sampling](https://mlsanity.com/paper/2609.21812/) (2026)
- [Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets](https://mlsanity.com/paper/2610.13590/) (2026)

## Abstract (arXiv)

We present an information-theoretic framework for sequential adaptive compressed sensing, Info-Greedy Sensing, where measurements are chosen to maximize the extracted information conditioned on the previous measurements. We show that the widely used bisection approach is Info-Greedy for a family of k-sparse signals by connecting compressed sensing and blackbox complexity of sequential query algorithms, and present Info-Greedy algorithms for Gaussian and Gaussian Mixture Model (GMM) signals, as well as ways to design sparse Info-Greedy measurements. Numerical examples demonstrate the good performance of the proposed algorithms using simulated and real data: Info-Greedy Sensing shows significant improvement over random projection for signals with sparse and low-rank covariance matrices, and adaptivity brings robustness when there is a mismatch between the assumed and the true distributions.