66 citations · 191 across the 14 of their papers we have counts for
4 papers · 1 filter
Ternary Residual Networks
Abhisek Kundu, Kunal Banerjee, Naveen Mellempudi +4
Sub-8-bit representation of DNNs incur some discernible loss of accuracy despite rigorous (re)training at low-precision. Such loss of accuracy essentially makes them equivalent to…
Recovering PCA from Hybrid- Sparse Sampling of Data Elements
Abhisek Kundu, Petros Drineas, Malik Magdon-Ismail
This paper addresses how well we can recover a data matrix when only given a few of its elements. We present a randomized algorithm that element-wise sparsifies the data, retaining…
Relaxed Leverage Sampling for Low-rank Matrix Completion
Abhisek Kundu
We consider the problem of exact recovery of any matrix of rank from a small number of observed entries via the standard nuclear norm minimization framework.…
A Note on Randomized Element-wise Matrix Sparsification
Abhisek Kundu, Petros Drineas
Given a matrix A \in R^{m x n}, we present a randomized algorithm that sparsifies A by retaining some of its elements by sampling them according to a distribution that depends on b…