Mukund Sundararajan | DeepAI

DeepAI AI Chat

Featured Co-authors

Li Zhang
240 publications
Pradeep Ravikumar
79 publications
Satyen Kale
25 publications
Chih-Kuan Yeh
15 publications
Ankur Taly
15 publications
Frederick Liu
15 publications
Walid Krichene
13 publications
Vineet Gupta
8 publications
Mihaela Curmei
7 publications
Kedar Dhamdhere
5 publications
Pramod Kaushik Mudrakarta
5 publications

∙ 09/17/2023

Private Matrix Factorization with Public Item Features

We consider the problem of training private recommendation models with a...

0 Mihaela Curmei, et al. ∙

∙ 06/09/2023

Using Foundation Models to Detect Policy Violations with Minimal Supervision

Foundation models, i.e. large neural networks pre-trained on large text ...

0 Sid Mittal, et al. ∙

∙ 05/24/2022

Attributing AUC-ROC to Analyze Binary Classifier Performance

Area Under the Receiver Operating Characteristic Curve (AUC-ROC) is a po...

0 Arya Tafvizi, et al. ∙

∙ 02/24/2022

First is Better Than Last for Training Data Influence

The ability to identify influential training examples enables us to debu...

0 Chih-Kuan Yeh, et al. ∙

∙ 02/19/2022

Reciprocity in Machine Learning

Machine learning is pervasive. It powers recommender systems such as Spo...

0 Mukund Sundararajan, et al. ∙

∙ 06/08/2020

The Penalty Imposed by Ablated Data Augmentation

There is a set of data augmentation techniques that ablate parts of the ...

0 Frederick Liu, et al. ∙

∙ 04/03/2020

Attribution in Scale and Space

We study the attribution problem [28] for deep networks applied to perce...

0 Shawn Xu, et al. ∙

∙ 02/19/2020

Estimating Training Data Influence by Tracking Gradient Descent

We introduce a method called TrackIn that computes the influence of a tr...

13 Garima Pruthi, et al. ∙

∙ 08/22/2019

The many Shapley values for model explanation

The Shapley value has become a popular method to attribute the predictio...

0 Mukund Sundararajan, et al. ∙

∙ 02/14/2019

A New Interaction Index inspired by the Taylor Series

We study interactions among players in cooperative games. We propose a n...

0 Ashish Agarwal, et al. ∙

∙ 06/11/2018

A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values

Local explanation methods, also known as attribution methods, attribute ...

0 Mukund Sundararajan, et al. ∙

∙ 05/30/2018

How Important Is a Neuron?

The problem of attributing a deep network's prediction to its input/base...

0 Kedar Dhamdhere, et al. ∙

∙ 05/14/2018

Did the Model Understand the Question?

We analyze state-of-the-art deep learning models for three tasks: questi...

0 Pramod Kaushik Mudrakarta, et al. ∙

∙ 03/12/2018

It was the training data pruning too!

We study the current best model (KDG) for question answering on tabular ...

0 Pramod Kaushik Mudrakarta, et al. ∙

∙ 09/28/2017

A Simple and Efficient MapReduce Algorithm for Data Cube Materialization

Data cube materialization is a classical database operator introduced in...

0 Mukund Sundararajan, et al. ∙

∙ 09/10/2017

Abductive Matching in Question Answering

We study question-answering over semi-structured data. We introduce a ne...

0 Kedar Dhamdhere, et al. ∙

∙ 11/08/2016

Gradients of Counterfactuals

Gradients have been used to quantify feature importance in machine learn...

0 Mukund Sundararajan, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world