Debarghya Mukherjee

Debarghya Mukherjee
University of Michigan | U-M · Department of Statistics

4th year Graduate Student

About

13
Publications
541
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2
Citations
Introduction
I am interested in concentration inequalities, empirical process theory, high dimensional statistics (especially for non-standard problem) and theoretical aspects of machine learning.
Additional affiliations
September 2017 - present
University of Michigan
Position
  • PhD Student
Description
  • I am interested in concentration inequalities, empirical process theory and high-dimensional statistics (especially for non-standard asymptotics) and machine learning theory.
Education
July 2015 - May 2017
Indian Statistical Institute
Field of study
  • Statistics

Publications

Publications (13)
Preprint
Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most problems are solved in discrete time, the underlying process is often continuous in nature. We exploit this underlying continuity by developing predictor-corrector algorith...
Preprint
Full-text available
Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions ca...
Preprint
Full-text available
Post-processing in algorithmic fairness is a versatile approach for correcting bias in ML systems that are already used in production. The main appeal of post-processing is that it avoids expensive retraining. In this work, we propose general post-processing algorithms for individual fairness (IF). We consider a setting where the learner only has a...
Preprint
Full-text available
This paper presents a number of new findings about the canonical change point estimation problem. The first part studies the estimation of a change point on the real line in a simple stump model using the robust Huber estimating function which interpolates between the $\ell_1$ (absolute deviation) and $\ell_2$ (least squares) based criteria. While...
Preprint
Full-text available
Regression discontinuity design models are widely used for the assessment of treatment effects in psychology, econometrics and biomedicine, specifically in situations where treatment is assigned to an individual based on their characteristics (e.g. scholarship is allocated based on merit) instead of being allocated randomly, as is the case, for exa...
Preprint
Full-text available
Optimal transport (OT) provides a way of measuring distances between distributions that depends on the geometry of the sample space. In light of recent advances in solving the OT problem, OT distances are widely used as loss functions in minimum distance estimation. Despite its prevalence and advantages, however, OT is extremely sensitive to outlie...
Preprint
Full-text available
One of the main barriers to the broader adoption of algorithmic fairness in machine learning is the trade-off between fairness and performance of ML models: many practitioners are unwilling to sacrifice the performance of their ML model for fairness. In this paper, we show that this trade-off may not be necessary. If the algorithmic biases in an ML...
Preprint
Full-text available
We study and predict the evolution of Covid-19 in six US states from the period May 1 through August 31 using a discrete compartment-based model and prescribe active intervention policies, like lockdowns, on the basis of minimizing a loss function, within the broad framework of partially observed Markov decision processes. For each state, Covid-19...
Preprint
Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barr...
Preprint
Linear thresholding models postulate that the conditional distribution of a response variable in terms of covariates differs on the two sides of a (typically unknown) hyperplane in the covariate space. A key goal in such models is to learn about this separating hyperplane. Exact likelihood or least square methods to estimate the thresholding parame...
Preprint
Full-text available
Manski's celebrated maximum score estimator for the binary choice model has been the focus of much investigation in both the econometrics and statistics literatures, but its behavior under growing dimension scenarios still largely remains unknown. This paper seeks to address that gap. Two different cases are considered: $p$ grows with $n$ but at a...

Network

Cited By