Madhusudhan Reddy Pittu

Postdoctoral Fellow, Industrial and Systems Engineering, Georgia Tech

prof_pic.jpg

madhusudhan.p@nyu.edu

Atlanta, GA

I am a Postdoctoral Fellow in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech, working with Mohit Singh. My appointment runs from September through December 2026. Previously, I was a Postdoctoral Associate at the Courant Institute of Mathematical Sciences, New York University, working with Anupam Gupta.

I received my Ph.D. in Computer Science from Carnegie Mellon University in the Algorithms, Combinatorics, and Optimization (ACO) program, advised by Anupam Gupta and, during my final year, David P. Woodruff. Prior to that, I earned my B.Tech. in Computer Science from the Indian Institute of Technology (IIT) Kharagpur.

My research interests lie broadly in Theoretical Computer Science, with a focus on Approximation Algorithms, Online Algorithms, Combinatorics, and Optimization. I am particularly interested in problems with a geometric flavor.

I am especially interested in AI research and engineering, with a focus on alignment and generalization. In an ongoing, unpublished project, I study unexpected, broad changes in model behavior arising from narrow fine-tuning. This work involves reproducing phenomena such as emergent misalignment and weird generalization on open-source models, mechanistic probing, and developing mathematical explanations. My goal is to understand and predict these effects, mitigate unwanted behavior, and develop better fine-tuning methods.

More broadly, I am excited to understand and use advances in AI to solve impactful real-world problems. I believe my background in theoretical computer science and mathematics can contribute to this effort.

Selected distinctions

  • Bronze Medal representing India at the 57th International Mathematical Olympiad, 2016
  • Infosys Award for excellent performance in International Olympiads, 2016
  • IITKGP Foundation-USA International Internship Award, 2020
  • Best Solution Award at the IMO training camp, 2015
  • Erdős number: 2

selected publications

  1. Combinatorial Optimization using Comparison Oracles
    Vincent Cohen-Addad, Tommaso d’Orsi, Anupam Gupta, and 7 more authors
    In Proceedings of the 58th Annual ACM Symposium on Theory of Computing, 2026
    STOC 2026, pp. 1995-2006.
  2. Guessing Efficiently for Constrained Subspace Approximation
    Aditya Bhaskara, Sepideh Mahabadi, Madhusudhan Reddy Pittu, and 2 more authors
    In 52nd International Colloquium on Automata, Languages, and Programming (ICALP 2025), 2025
    LIPIcs 334, Article 29, pp. 29:1-29:20.
  3. Approximation Algorithms for the Weighted Nash Social Welfare via Convex and Non-Convex Programs
    Adam Brown, Aditi Laddha, Madhusudhan Reddy Pittu, and 1 more author
    In Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2024
    SODA 2024, pp. 1307-1327. The full journal version appears separately above.
  4. The Price of Explainability for Clustering
    Anupam Gupta, Madhusudhan Reddy Pittu, Ola Svensson, and 1 more author
    In 2023 IEEE 64th Annual Symposium on Foundations of Computer Science (FOCS), 2023
    FOCS 2023, pp. 1131-1148.
  5. Determinant Maximization via Matroid Intersection Algorithms
    Adam Brown, Aditi Laddha, Madhusudhan Pittu, and 2 more authors
    In 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS), 2022
    FOCS 2022, pp. 255-266.
  6. A 3-Approximation Algorithm for Maximum Independent Set of Rectangles
    Waldo Gálvez, Arindam Khan, Mathieu Mari, and 3 more authors
    In Proceedings of the 2022 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2022
    SODA 2022, pp. 894-905. The arXiv link is pinned to version 2, which matches this title.