Scholar
Ainesh Bakshi
Google Scholar ID: hr81fHoAAAAJ
Massachusetts Institute of Technology
Citations & Impact
Citations
830
H-index
17
i10-index
22
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Published multiple papers in top international conferences such as SODA, COLT, STOC, QIP, FOCS, ICML, NeurIPS, etc. Specific publications include:
- - Additive Approximation Schemes for Low-Dimensional Embeddings
- - Metric Embeddings Beyond Bi-Lipschitz Distortion via Sherali-Adams
- - Sample-Optimal Private Regression in Polynomial Time
- - Learning the Closest Product State
- - High-Temperature Gibbs States are Unentangled and Efficiently Preparable
- - Efficient Certificates of Anti-Concentration Beyond Gaussians
- - Structure learning of Hamiltonians from real-time evolution
- - Learning Quantum Hamiltonians at any Temperature in Polynomial Time
- - An Improved Classical Singular Value Transform for Quantum Machine Learning
- - A Near-Linear Time Algorithm for the Chamfer Distance
- - Krylov Methods are (nearly) Optimal for Low-Rank Approximation
- - Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
- - A New Approach to Learning a Linear Dynamical System
- - Sub-Quadratic Algorithms for Kernel Matrices via Kernel Density Estimation
- - Low-Rank Approximation with 1/epsilon^(1/3) Matrix-Vector Products
- - Robustly Learning Mixtures of k Arbitrary Gaussians
- - Robust Linear Regression: Optimal Rates in Polynomial Time
- - Learning a Latent Simplex in Input Sparsity
Research Experience
- Assistant Professor at NYU; Postdoctoral Fellow at MIT.
Education
- PhD in Computer Science from CMU; Postdoctoral Fellow in Mathematics and EECS at MIT before joining NYU.
Background
- I am an Assistant Professor in the Computer Science Department at NYU, where I am part of the Theory Group. I am broadly interested in Theoretical Computer Science and Quantum Information. My main research thread revolves around using the algorithmic toolkit, consisting of iterative methods and convex relaxations, to understand quantum systems. I am also interested in applying this toolkit to high-dimensional statistics, metric embedding, and numerical linear algebra problems.
Miscellany
- Looking for strong theory students starting in Fall 2026. Interested applicants can apply to the NYU CS PhD Program and mention my name in the application. Prospective applicants can signal their interest via a form.
Co-authors