Corpus ID: 211082829

# List-Decodable Subspace Recovery via Sum-of-Squares

@article{Bakshi2020ListDecodableSR,
title={List-Decodable Subspace Recovery via Sum-of-Squares},
author={Ainesh Bakshi and Pravesh Kothari},
journal={ArXiv},
year={2020},
volume={abs/2002.05139}
}
• Published in ArXiv 2020
• Computer Science, Mathematics
• We give the first efficient algorithm for the problem of list-decodable subspace recovery. Our algorithm takes input $n$ samples $\alpha n$ ($\alpha\ll 1/2$) are generated i.i.d. from Gaussian distribution $\mathcal{N}(0,\Sigma_*)$ on $\mathbb{R}^d$ with covariance $\Sigma_*$ of rank $r$ and the rest are arbitrary, potentially adversarial outliers. It outputs a list of $O(1/\alpha)$ projection matrices guaranteed to contain a projection matrix $\Pi$ such that \$\|\Pi-\Pi_*\|_F^2 = \kappa^4 \log… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

#### References

##### Publications referenced by this paper.
SHOWING 1-10 OF 43 REFERENCES

## Faster Algorithms for High-Dimensional Robust Covariance Estimation

• Computer Science, Mathematics
• COLT
• 2019

## List Decodable Learning via Sum of Squares

• Mathematics, Computer Science
• SODA
• 2020

## High-Dimensional Robust Mean Estimation in Nearly-Linear Time

• Computer Science, Mathematics
• SODA
• 2019

## List-decodable linear regression, CoRR abs/1905.05679 (2019)

• Sushrut Karmalkar, Adam R. Klivans, Pravesh K. Kothari
• 2019

## An Overview of Robust Subspace Recovery

• Mathematics, Computer Science
• Proceedings of the IEEE
• 2018

## Efficient algorithms for outlierrobust regression, Conference On Learning Theory, COLT 2018

• Adam R. Klivans, Pravesh K. Kothari, Raghu Meka
• Stockholm, Sweden,
• 2018

## Robust Estimation via Robust Gradient Estimation

• Mathematics, Computer Science
• ArXiv
• 2018

## Static and Dynamic Robust PCA and Matrix Completion: A Review

• Mathematics, Computer Science
• Proceedings of the IEEE
• 2018