Pranjal Awasthi

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness

Alongside the well-publicized accomplishments of deep neural networks th...
03/01/2021 ∙ by Jacob Abernethy, et al. ∙ 0 ∙ share

read it
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information

Training and evaluation of fair classifiers is a challenging problem. Th...
02/16/2021 ∙ by Pranjal Awasthi, et al. ∙ 16 ∙ share

read it
Adversarial Robustness Across Representation Spaces

Adversarial robustness corresponds to the susceptibility of deep neural ...
12/01/2020 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Beyond Individual and Group Fairness

We present a new data-driven model of fairness that, unlike existing sta...
08/21/2020 ∙ by Pranjal Awasthi, et al. ∙ 8 ∙ share

read it
On the Rademacher Complexity of Linear Hypothesis Sets

Linear predictors form a rich class of hypotheses used in a variety of l...
07/21/2020 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Adaptive Sampling to Reduce Disparate Performance

Existing methods for reducing disparate performance of a classifier acro...
06/11/2020 ∙ by Jacob Abernethy, et al. ∙ 1 ∙ share

read it
A Notion of Individual Fairness for Clustering

A common distinction in fair machine learning, in particular in fair cla...
06/08/2020 ∙ by Matthäus Kleindessner, et al. ∙ 0 ∙ share

read it
Estimating Principal Components under Adversarial Perturbations

Robustness is a key requirement for widespread deployment of machine lea...
05/31/2020 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks

Adversarial or test time robustness measures the susceptibility of a cla...
04/28/2020 ∙ by Pranjal Awasthi, et al. ∙ 5 ∙ share

read it
Efficient active learning of sparse halfspaces with arbitrary bounded noise

In this work we study active learning of homogeneous s-sparse halfspaces...
02/12/2020 ∙ by Chicheng Zhang, et al. ∙ 11 ∙ share

read it
A Deep Conditioning Treatment of Neural Networks

We study the role of depth in training randomly initialized overparamete...
02/04/2020 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Adversarially Robust Low Dimensional Representations

Adversarial or test time robustness measures the susceptibility of a mac...
11/29/2019 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
On Robustness to Adversarial Examples and Polynomial Optimization

We study the design of computationally efficient algorithms with provabl...
11/12/2019 ∙ by Pranjal Awasthi, et al. ∙ 16 ∙ share

read it
Effectiveness of Equalized Odds for Fair Classification under Imperfect Group Information

Most approaches for ensuring or improving a model's fairness with respec...
06/07/2019 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Guarantees for Spectral Clustering with Fairness Constraints

Given the widespread popularity of spectral clustering (SC) for partitio...
01/24/2019 ∙ by Matthäus Kleindessner, et al. ∙ 0 ∙ share

read it
Fair k-Center Clustering for Data Summarization

In data summarization we want to choose k prototypes in order to summari...
01/24/2019 ∙ by Matthäus Kleindessner, et al. ∙ 0 ∙ share

read it
Bilu-Linial stability, certified algorithms and the Independent Set problem

We study the notion of Bilu-Linial stability in the context of Independe...
10/19/2018 ∙ by Haris Angelidakis, et al. ∙ 0 ∙ share

read it
Towards Learning Sparsely Used Dictionaries with Arbitrary Supports

Dictionary learning is a popular approach for inferring a hidden basis o...
04/23/2018 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Robust Vertex Enumeration for Convex Hulls in High Dimensions

Computation of the vertices of the convex hull of a set S of n points in...
02/05/2018 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Clustering Semi-Random Mixtures of Gaussians

Gaussian mixture models (GMM) are the most widely used statistical model...
11/23/2017 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
On some provably correct cases of variational inference for topic models

Variational inference is a very efficient and popular heuristic used in ...
03/23/2015 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
The Power of Localization for Efficiently Learning Linear Separators with Noise

We introduce a new approach for designing computationally efficient lear...
07/31/2013 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it
Learning using Local Membership Queries

We introduce a new model of membership query (MQ) learning, where the le...
11/05/2012 ∙ by Pranjal Awasthi, et al. ∙ 0 ∙ share

read it

Pranjal Awasthi

Featured Co-authors

Jie Zhang

Yishay Mansour

Jie Shen

Mehryar Mohri

Maria-Florina Balcan

Vitaly Feldman

Andrej Risteski

Da-Cheng Juan

Naman Agarwal

Varun Kanade

Avrim Blum

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness

Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information

Adversarial Robustness Across Representation Spaces

Beyond Individual and Group Fairness

On the Rademacher Complexity of Linear Hypothesis Sets

Adaptive Sampling to Reduce Disparate Performance

A Notion of Individual Fairness for Clustering

Estimating Principal Components under Adversarial Perturbations

Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks

Efficient active learning of sparse halfspaces with arbitrary bounded noise

A Deep Conditioning Treatment of Neural Networks

Adversarially Robust Low Dimensional Representations

On Robustness to Adversarial Examples and Polynomial Optimization

Effectiveness of Equalized Odds for Fair Classification under Imperfect Group Information

Guarantees for Spectral Clustering with Fairness Constraints

Fair k-Center Clustering for Data Summarization

Bilu-Linial stability, certified algorithms and the Independent Set problem

Towards Learning Sparsely Used Dictionaries with Arbitrary Supports

Robust Vertex Enumeration for Convex Hulls in High Dimensions

Clustering Semi-Random Mixtures of Gaussians

On some provably correct cases of variational inference for topic models

The Power of Localization for Efficiently Learning Linear Separators with Noise

Learning using Local Membership Queries