
Ainesh Bakshi
Email: abakshi (at) cs (dot) cmu (dot) edu
Office: GHC 5103

I am a fourth year PhD student at Carnegie Mellon University. I am extremely fortunate to be coadvised by Pravesh Kothari and David Woodruff. I am broadly interested in Theoretical Computer Science and
my current research interests are algorithms for randomized linear algebra, convex relaxations, the sumofsquares meta algorithm and provable guarantees for learning problems.
Previously, I was an undergrad at Rutgers, New Brunswick, where I had the pleasure of working with Martin FarachColton
and Pranjal Awasthi on external memory algorithms and clustering respectively.
Publications
 Robustly Learning Mixtures of k Arbitrary Gaussians
Ainesh Bakshi, Ilias Diakonikolas, He Jia, Daniel Kane, Pravesh Kothari and Santosh Vempala
Preprint [arXiv].
 Robust Linear Regression: Optimal Rates in Polynomial Time
Ainesh Bakshi, Adarsh Prasad
STOC 2021 [arXiv].
 Learning a Latent Simplex in Input Sparsity Time
Ainesh Bakshi, Chiranjib Bhattacharyya, Ravi Kannan, David Woodruff and Samson Zhou
ICLR 2021, Selected for Spotlight Presentation.
 ListDecodable Subspace Recovery: Dimension Independent Error in Polynomial Time
Ainesh Bakshi, Pravesh Kothari
SODA 2021 [arXiv].
 Testing Positive SemiDefiniteness via Random Submatrices
Ainesh Bakshi, Nadiia Chepurko, Rajesh Jayaram
FOCS 2020 [arXiv].
 OutlierRobust Clustering of Nonspherical Mixtures
Ainesh Bakshi, Pravesh Kothari
FOCS 2020 [arXiv], [Joint Talk @ FOCS'20], [Long Talk @ TTIC]
Conference version to be merged with this paper.
 Robust and Sample Optimal Algorithms for PSD Low Rank Approximation
Ainesh Bakshi, Nadiia Chepurko, David Woodruff
FOCS 2020 [arXiv], [Talk @ WOLA'20], [Joint Talk @ FOCS'20].
 Weighted Maximum Independent Set of Geometric Objects in Turnstile Streams
Ainesh Bakshi, Nadiia Chepurko, David Woodruff
APPROX 2020 [arXiv] [Talk @ Approx].
 Robust CommunicationOptimal Distributed Clustering Algorithms
Pranjal Awasthi, Ainesh Bakshi, Nina Balcan, Colin White, David Woodruff
ICALP 2019 [arXiv].
 Learning Two Layer Rectified Neural Networks in Polynomial Time
Ainesh Bakshi, Rajesh Jayaram,
David Woodruff
COLT 2019 [arXiv].
 Sublinear Time LowRank Approximation of Distance Matrices
Ainesh Bakshi,
David Woodruff
NeurIPS 2018, Selected for Spotlight Presentation [arXiv], [Talk @ CMU TL].
Undergraduate Work

"How to Fragment your File System"
A. Conway,
A. Bakshi,
Y. Jiao,
Y. Zhan,
M. Bender,
W. Jannen,
R. Johnson,
B. Kuzmaul,
D. Porter,
J. Yuan,
M. FarachColton
;login: magazine, vol. 42(2), 2017.

"File Systems fated for Senescence? Nonsense, Says Science!"
A. Conway,
A. Bakshi,
Y. Jiao,
Y. Zhan,
M. Bender,
W. Jannen,
R. Johnson,
B. Kuzmaul,
D. Porter,
J. Yuan,
M. FarachColton
Proceedings of the 15th USENIX Conference on File and Storage Technologies (FAST '17), Santa Clara, CA, February 2017.
Teaching