project . 2019 - 2025 . On going

SO-ReCoDi

Spectral and Optimization Techniques for Robust Recovery, Combinatorial Constructions, and Distributed Algorithms
Open Access mandate for Publications and Research DataOpen Access mandate for ... European Commission
  • Funder: European CommissionProject code: 834861 Call for proposal: ERC-2018-ADG
  • Funded under: H2020 | ERC | ERC-ADG Overall Budget: 1,971,800 EURFunder Contribution: 1,971,800 EUR
  • Status: On going
  • Start Date
    01 Sep 2019
    End Date
    28 Feb 2025
  • Detailed project information (CORDIS)
Description
In a recovery problem, we are interested in recovering structure from data that contains a mix of combinatorial structure and random noise. In a robust recovery problem, the data may contain adversarial perturbations as well. A series of recent results in theoretical computer science has led to algorithms based on the convex optimization technique of Semidefinite Programming for several recovery problems motivated by unsupervised machine learning. Can those algorithms be made robust? Sparsifiers are compressed representations of graphs that speed up certain algorithms. The recent proof of the Kadison-Singer conjecture by Marcus, Spielman and Srivastava (MSS) sho...
Description
In a recovery problem, we are interested in recovering structure from data that contains a mix of combinatorial structure and random noise. In a robust recovery problem, the data may contain adversarial perturbations as well. A series of recent results in theoretical computer science has led to algorithms based on the convex optimization technique of Semidefinite Programming for several recovery problems motivated by unsupervised machine learning. Can those algorithms be made robust? Sparsifiers are compressed representations of graphs that speed up certain algorithms. The recent proof of the Kadison-Singer conjecture by Marcus, Spielman and Srivastava (MSS) sho...
Any information missing or wrong?Report an Issue