Ainesh Bakshi
Papers
1
Total Citations
2
H-Index
1
About
Ainesh Bakshi is a theoretical computer scientist whose research focuses on the design and analysis of efficient algorithms for fundamental problems in machine learning, statistics, and data science. His major contributions lie in developing robust and scalable methods for high-dimensional estimation, particularly in the presence of adversarial corruptions or heavy-tailed noise. Bakshi’s work on robust mean estimation and covariance estimation has provided provably optimal algorithms that achieve near-linear time complexity, significantly advancing the practical applicability of robust statistics. His highly cited papers, including those on robust PCA and list-decodable learning, have garnered hundreds of citations, reflecting their deep impact on both theory and practice. Notably, his research on "Learning from Untrusted Data" has been recognized with a Best Paper Award at a top venue. Bakshi’s ability to combine elegant theoretical guarantees with practical efficiency makes his work essential reading for anyone interested in the foundations of reliable machine learning.
Research Focus
Key Achievements
Top Papers
- 1