Vivek Bharadwaj — accepted AI-conference papers

2024

Efficient Leverage Score Sampling for Tensor Train Decomposition

Vivek Bharadwaj, Beheshteh T. Rakhshan, Osman Asif Malik, Guillaume Rabusseau

NeurIPS 2024poster

Tensor Train~(TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently compress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squa…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition

Vivek Bharadwaj, Osman Asif Malik, Riley Murray, Laura Grigori, Aydin Buluc, James Demmel

NeurIPS 2023poster

We present a data structure to randomly sample rows from the Khatri-Rao product of several matrices according to the exact distribution of its leverage scores. Our proposed sampler draws each row in time logarithmic in the height of the Khatri-Rao product and quadratic in its column count, with pers…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗