Arpita Gang

Machine Learning Scientist currently working in Visa Inc. USA. I completed my PhD from Rutgers University, New Brunswick in 2022. My research interests lie in the field of statistical machine learning, graph machine learning, distributed optimization and signal processing.

General Info

  • Date of BirthApril 19
  • LocationAustin, TX
  • E-mailarpitagang19@gmail.com
5

Work Experience

  • 2018-2022

    Rutgers University

    Graduate Research Assistant

    Working on feature learning and dimension reduction techniques for big data in distributed settings. Developing a distrbuted training system for autoencoder for feature learning. Focus is to develop efficient algorithms as well as analyze their mathematical convergence guarantees.

  • 2017-2018

    Rutgers University

    Teaching Assistant

    Assisted in teaching the course and conducting labs for the courses Digital Signal Processing and Principle of Electrical Engineering.

  • 2016-2017

    Indraprastha Institute of Information Technology, Delhi

    Research Assistant

    Used dictionary learning and deep learning techniques on the single channel audio source separation problem.

  • 2014-2016

    Indraprastha Institute of Information Technology, Delhi

    Teaching Assistant

    Assisted in teaching the course and conducting labs for the courses Principle of Communication Systems and Modeling Complex Systems.

Education

  • 2017-Present

    Doctor of Philosophy

    Rutgers University

    Department of Electrical and Computer Engineering.
    Research Area: Machine Learning and Distributed Optimization.
    Courses: Linear Algebra, Machine Learning, Information Theory and Coding, Stochastic Signals and Systems, Real Analysis, Optimum Signal Processing, Quantum Information Science.
    GPA: 3.92/4

  • 2014-2016

    Master of Technology

    Indraprastha Institute of Information Technology, Delhi, India

    Department of Electronics and Communication Engineering.
    Major: Communication and Signal Processing.
    Courses: Convex Optimization, Probability and Random Processes, Statistical Signal Processing, Compressive Sensing, Stochastic Estimation and Control.
    GPA: 9.44/10

  • 2009-2013

    Bachelor of Technology

    National Institute of Technology, Silchar, India

    Department of Electronics and Communication Engineering.
    GPA: 9.16/10

Projects

  • Predicting missing features

    Graduate Course Project

    Cleaned a given heterogenous dataset consisting of categorical, ordinal, binary, textual features.
    Feature Engineering to make the data usual in machine learning algorithms.
    Built a whole system consisting of various modules like classfication, regression etc. to predict the missing features in the data.

  • Road Intersection Detection

    Independent Project

    Part of an autonomous vehicle project.
    Used LIDAR and image data to detect lanes for road navigation.

  • Recovering EEG Signals

    Graduate Course Project

    Used dictionary learning and orthogonal matching pursuit for recovering EEG signals from partially sampled data.

  • Speaker Verification System

    Undergraduate Project

    Developed a text-based speaker verification model that can be used for systems that need user authentication .

Publications

  1. Arpita Gang, Waheed U. Bajwa, ``FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis", arXiv preprint arXiv:2108.12373, Aug 2021.
  2. Arpita Gang, Bingqing Xiang and Waheed. U. Bajwa, "Distributed Principal Subspace Analysis for Partitioned Big Data: Algorithms, Analysis, and Implementation," in IEEE Transactions on Signal and Information Processing over Networks, vol. 7, pp. 699-715, 2021, doi: 10.1109/TSIPN.2021.3122297.
  3. Arpita Gang, Waheed U. Bajwa, “A linearly convergent algorithm for distributed principal component analysis”, Signal Processing, Volume 193, 2022, 108408, ISSN 0165-1684.
  4. Zhixiong Yang, Arpita Gang, Waheed .U. Bajwa, "Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model," in IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 146-159, May 2020
  5. Arpita Gang, Haroon Raja and Waheed U. Bajwa, "Fast and Communication-efficient Distributed PCA", 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 7450-7454.
  6. Arpita Gang, Pravesh Biyani, Akshay Soni, "Towards Automated Single Channel Source Separation Using Neural Networks" Proc. Interspeech 2018, 3494-3498
  7. Arpita Gang, Pravesh Biyani, "On Discriminative Framework for Single Channel Audio Source Separation" Proc. Interspeech 2016, 565-569
  8. Ramanjit Ahuja, Arpita Gang, Pravesh Biyani and Surendra Prasad, "A fast converging method for common mode sensor based impulse noise cancellation for downstream VDSL" 2016 24th European Signal Processing Conference (EUSIPCO), Budapest, 2016, pp. 310-315

Skills and Certificates

  • Programming Languages: Python, MATLAB, C
  • Frameworks: Numpy, Tensorflow, Keras, Matplotlib
  • Course Certifications: Reinforcement Learning, Data Structures
  • Others: Git, LaTeX

Awards

  • Scholarship to attend CRA-WP Grad Cohort for Women Workshop, 2021
  • Grace Hopper Scholarship 2020.
  • TA/GA Professional Development Fund, Rutgers University, 2018.
  • Google Travel Grant for INTERSPEECH 2016.
  • Silver Medal in Undergrad, NIT Silchar.

Extra-Curricular

  • Mentored two junior students at INSPIRE Lab, ECE, Rutgers University.
  • Organizer of SIP seminar series in ECE department of Rutgers University, 2018-2019.
  • Reviewer for multiple journals (TSP, TSIPN, Signal Processing) and conferences (ICASSP, ICML, Asilomar).
  • Personal Blog: musingsbyarpita.com
  • Trained in Indian Classical Dance Form (Kathak)
  • Hobbies: Reading, Dancing, Sketching