activity
20152019
most citedTight Continuous Relaxation of the Balanced -Cut Problem

11 citations · 13 across the 2 of their papers we have counts for

collaborators

5 papers

math.NA20192 cited

Asymmetric Multiresolution Matrix Factorization

Pramod Kaushik Mudrakarta, Shubhendu Trivedi, Risi Kondor

Multiresolution Matrix Factorization (MMF) was recently introduced as an alternative to the dominant low-rank paradigm in order to capture structure in matrices at multiple differe…

cs.LG2018

K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning

Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov +1

We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set…

cs.CL2018

Did the Model Understand the Question?

Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (wo…

cs.LG2018

It was the training data pruning too!

Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1

We study the current best model (KDG) for question answering on tabular data evaluated over the WikiTableQuestions dataset. Previous ablation studies performed against this model a…

stat.ML201511 cited

Tight Continuous Relaxation of the Balanced -Cut Problem

Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein

Spectral Clustering as a relaxation of the normalized/ratio cut has become one of the standard graph-based clustering methods. Existing methods for the computation of multiple clus…