Abhinav Agrawal
Abhinav Agrawal

PhD in Computer Science

University of Massachusetts Amherst

About Me

I’m a final year Ph.D. student in Computer Science at University of Massachusetts Amherst, advised by Prof. Justin Domke.

I am broadly interested in machine learning. My research work focuses on leveraging generative modeling approaches to build better sampling methods. Recently, I was also involved in building India’s leading AI tutor app during time at SigIQ.ai. Prior to that I spent a wonderful summer with the Causality and Machine Learning team at Microsoft Research Redmond, and another summer as an applied scientist intern with the personalization team at Amazon.

Before my graduate studies, I spent four amazing years at IIT Kanpur acquiring background in machine learning and electrical engineering. During this time, I was mentored by Prof. Piyush Rai, Prof. Tanay Guha, and Prof. Vinay P. Namboodiri (undergraduate thesis advisor).

Aside from work, I enjoy keeping myself fit, reading books, making people laugh, and playing board games. I cherish deep, philosophical discussions (including but not limited to AI and its implications :)). Feel free to reach out to me and I will be more than happy to lend an ear.

Interests
  • Building AI products
  • Generative Modeling
  • Variational Inference
Education
  • PhD in Computer Science

    UMass Amherst

  • Masters in Computer Science

    UMass Amherst

  • B.Tech in Electrical Engineering

    IIT Kanpur

Selected Publications
(2021). Amortized Variational Inference in Hierarhical Distributions. In NeurIPS 2021.
(2020). Normalizing Flows Across Dimensions. In Workshop, ICML, 2020.

Experience

  1. PhD in Computer Science

    University of Massachusetts Amherst
  2. Product Lead

    SigIQ.ai
  3. Research Intern

    Microsoft Research Redmond
  4. Applied Scientist Intern

    Amazon
  5. Master in Computer Science

    University of Massachusetts Amherst
  6. Undergraduate Research Assistant

    University of Texas at Dallas