avatar

Purva Pruthi

Ph.D. Candidate
UMass Amherst
ppruthi(at) cs.umass.edu


About Me

I am a final year Ph.D. candidate at the Computer Science department at University of Massachusetts, Amherst, advised by David Jensen. My research combines causality, compositional reasoning and modular deep learning to develop efficient and scalable causal models for complex real-world systems such as databases, software programs, and manufacuring assembly system. I am also interested in out-of-distribution generalization, and understanding theoretical characteristics of modular models as compared to non-modular models in machine learning.

Previously, I was an AI resident at Google X, The Moonshot Factory, working on causal inference applications in agriculture and biology. I also interned at Amazon Cambridge (Summer 2018), working with Javier Gonzalez and Xiaoyu Lu on developing a transfer-learning framework for reinforcement learning. I have also worked with Madalina Fiterau at the intersection of causal reasoning and healthcare. Before my Ph.D., I spent three years at Goldman Sachs building statistical models for systematic trading and trade settlement analysis. Outside work, I enjoy writing prose poetry, reading books, playing piano, and doing yoga!

Publications

  1. CLeaR
    Purva Pruthi and David Jensen
    Conference on Causal Learning and Reasoning (CLeaR), 2025.

  2. ICML
    Amanda Gentzel, Purva Pruthi, and David Jensen
    International Conference on Machine Learning (ICML), 2021.

  3. ICML Workshop
    Purva Pruthi, Javier González, Xiaoyu Lu, and Madalina Fiterau
    ICML 2020 Workshop on Inductive Biases, Invariances and Generalization in Reinforcement Learning

News

Services and Outreach


Powered by Jekyll and Minimal Light theme.