Research
Broadly, I am interested in designing efficient algorithms with provable guarantees for problems in data science and machine learning.
More specifically, I have worked on sketching and coreset methods for problems in randomized numerical linear algebra, optimization and machine learning.
|
Projective Clustering Product Quantization
Aditya Krishnan, Edo Liberty
In Submission, 2021
|
Sublinear Time Spectral Density Estimation
Vladimir Braverman, Aditya Krishnan, Christopher Musco
ACM Symposium on Theory of Computing (STOC), 2022
|
Lifelong Learning with Sketched Structural Regularization
Haoran Li, Aditya Krishnan, Jingfeng Wu, Soheil Kolouri, Praveen K. Pilly, Vladimir Braverman
Asian Conference in Machine Learning (ACML), 2021
|
Near-Optimal Entrywise Sampling of Numerically Sparse Matrices
Vladimir Braverman, Robert Krauthgamer, Aditya Krishnan, Shay Sapir
Conference on Learning Theory (COLT), PMLR, 2021
|
Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension
Vladimir Braverman, Robert Krauthgamer, Aditya Krishnan, Roi Sinoff
International Conference on Machine Learning (ICML), 2020
|
Competitively Pricing Parking in a Tree
Max Bender, Jacob Gilbert, Aditya Krishnan, Kirk Pruhs
Conference on Web and Internet Economics (WINE), 2020
|
On Sketching the q to p Norms
Aditya Krishnan, Sidhanth Mohanty, David P. Woodruff
International Conference on Approximation Algorithms for Combinatorial Optimization Problems (APPROX), 2018
|
|
Teaching Assistant, 601.433/601.633 Introduction to Algorithms: F19, S20, S22
Teaching Assistant, 601.435/601.635 Approximation Algorithms: S21
Co-organizer, JHU CS Theory Seminar, F21, S22
|
|