Support Recovery of Sparse Signals from a Mixture of Linear Measurements

Authors: Soumyabrata Pal, Arya Mazumdar, Venkata Gandikota

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide algorithms that use a number of measurements polynomial in k, log n and quasi-polynomial in , to recover the support of all the unknown vectors in the mixture with high probability when each individual component is a k-sparse n-dimensional vector. In Section 3, we provided the detailed proofs of Theorem 1 (Section 3.1), Theorem 3 (Section 3.2) and Theorem 4 (Section 3.3) while deferring the proof of Theorem 2 to Appendix D.
Researcher Affiliation Academia Venkata Gandikota Electrical Engineering & Computer Science Syracuse University Syracuse, NY 13210 gandikota.venkata@gmail.com; Arya Mazumdar Halıcıoğlu Data Science Institute University of California, San Diego La Jolla, CA 92093 arya@ucsd.edu; Soumyabrata Pal College of Information & Computer Sciences University of Massachusetts Amherst Amherst, MA 01003 soumyabratap@umass.edu
Pseudocode Yes Algorithm 1 RECOVER p-IDENTIFIABLE SUPPORTS, Algorithm 2 RECOVER FLIP-INDEPENDENT SUPPORTS, Algorithm 3 RECOVER r-KRUSKAL RANK SUPPORTS
Open Source Code No The paper does not provide any explicit statements about making the source code available or links to a code repository for the methodology described.
Open Datasets No The paper is theoretical and does not conduct experiments on datasets, thus it does not mention public dataset availability for training.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments, therefore it does not discuss training/validation/test dataset splits.
Hardware Specification No The paper discusses theoretical computational complexity (Remark 5) but does not provide any specific details about the hardware used for computations or experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs, thus it does not include details on experimental setup such as hyperparameters or training configurations.