About

This is Meenal, my pronouns are She/Her. I’m a 19 year old junior at University of Delhi, majoring in CS and math. My interests are centered around the following:

• Computational Geometry and Spectral Graph theory in the design and analysis of Discrete Algorithms, their utilities in representation learning. These days I’m focussing on Manifold Learning with applications in Computational Linguistics and Algorithmic Fairness.

• I’m enthusiastic about open source projects and Probabilistic Programming. I spend some time learning Bayesian Inference and working with PyMC. We’re releasing a new version!!

• I’ve been thinking about tools for thought and trying to write my notes publicly. Also, I really like words and write a bit of poetry, I would love it if you checked that out!! I’m also open to new projects or collaborations. If you just want to chat about any of the above or rant about systemic oppression, drop me a mail at: meenal[at]mjhajharia[dot]com

Recent Experience / Projects

TIME SERIES MODELING

Extending Bayesian Time Series Models of PyMC3: Implementing a new class of models - SARIMAX, Kalman filter and state space implementation. Alongside, I’m working on Pedagogical notebooks exploring the econometric applications of these models.[Project]

INDIAN STATISTICAL INSTITUTE

Worked with Prof. Ujjwal Maulik and Prof. Sanghamitra Bandyopadhya (Director, ISI Kolkata) on Non Linear Dimensionality Reduction- Algorithms based on canonical feature extraction techniques such as PCA and LDA applied through Graph Embedding.

UNSUPERVISED KEYWORD EXTRACTION

Developed an Unsupervised, graph-based algorithm for Keyphrase Extraction that exploits syntactic relations using dependency parsing, augmented with local text attributes. We reconstruct dependency trees in a Hyperbolic metric space to locate keywords, further ranked by statistical NLP features.[pdf]

REFERENCE MANAGEMENT TOOL

A Viola Dashboard with LDA based topic modeling for editing, organizing and viewing research papers. MySQL and Python backend for automatic retrieval of metadata from PDFs scraping through Google Scholar and CrossRef.

MODELING MOVEMENT OF AQUATIC ECOSYSTEMS

Modeling the movement of Pelagic fish stocks in North Atlantic ocean for the next fifty years by analysing the rise in global and local temperatures as an effect of global warming, suggesting relocation for small fisheries accordingly. This project was the only one to recieve an honourable mention from India at COMAP

SUDOKUS AND GRAPH THEORY

Interpreting a Sudoku as an NP Graph coloring problem, visualization using networkx, and working through the Chromatic Polynomial to analyse the number of puzzles or solutions possibly generated with varying number of clues.