Arvind V. Mahankali

activity

20192026

most citedOne Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

2 citations · 4 across the 6 of their papers we have counts for

collaborators

Showing cs.DSShow all

3 papers · 1 filter

cs.DS2022

Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions

Arvind V. Mahankali, David P. Woodruff, Ziyu Zhang

We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor netw…

cs.DS2021

Streaming and Distributed Algorithms for Robust Column Subset Selection

Shuli Jiang, Dongyu Li, Irene Mengze Li +2

We give the first single-pass streaming algorithm for Column Subset Selection with respect to the entrywise $ℓ_{p}$ -norm with $1 \leq p < 2$ . We study the $ℓ_{p}$ norm loss since…

cs.DS2020

Optimal $ℓ_{1}$ Column Subset Selection and a Fast PTAS for Low Rank Approximation

Arvind V. Mahankali, David P. Woodruff

We study the problem of entrywise $ℓ_{1}$ low rank approximation. We give the first polynomial time column subset selection-based $ℓ_{1}$ low rank approximation algorithm samplin…

Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions

Streaming and Distributed Algorithms for Robust Column Subset Selection

Optimal ℓ1​ Column Subset Selection and a Fast PTAS for Low Rank Approximation

Optimal $ℓ_{1}$ Column Subset Selection and a Fast PTAS for Low Rank Approximation