Ani Sridhar

Postdoc @ MIT Mathematics

prof_pic.jpg

MIT 2-246A

anisri@mit.edu

I am a postdoctoral associate at the Mathematics Department at MIT, working with Elchanan Mossel. Previously, I completed my PhD at Princeton’s Department of Electrical and Computer Engineering, where I was advised by Miklós Z. Rácz and Vince Poor. My research uses tools from probability, statistics and graph theory to tackle fundamental challenges in network analysis, causal inference and epidemiology. Recent and ongoing research directions include:

  • Modeling complex systems. In socioeconomic, biological and engineering systems, fascinating aggregate trends arise from microscopic behaviors. However, traditional population models do not account for the complex ways in which individuals interact with each other. My research explores how new models can be developed to capture the impact of these complex interactions on the system as a whole. I am also interested in interpretable characterizations of complex systems through these models, such as macroscopic behaviors, long-term trends, and the probabilities of critical events.
  • Real-time inference of dynamical systems. The data we observe from complex systems is often noisy and incomplete. How can important real-time inferences and decisions be made in spite of this uncertainty? I have explored several variations of this question in the context of non-stationary processes on networks (e.g., viral spread), which have led to new methods for change-point detection and parameter learning.
  • Graph matching. How can structural similarities be found across networks, and what can we learn from the commonalities? My research characterizes the precise information-theoretic thresholds for the possibility or impossibility of this question and related ones, such as community detection or clustering.

For additional details, you can check out my CV or my Google Scholar page.

news

Oct 20, 2024 I will be giving a talk on mean-field approximations and chairing a session on Networks, Dynamics and Inference at the Informs 2024 conference.
Jun 30, 2024 New paper on finding super-spreaders in network cascades to be presented at COLT 2024. Joint work with Elchanan Mossel (MIT).
Mar 14, 2024 Speaking about quickly tracking network cascades at a session on Advances in Sequential Analysis and Change Point Detection at the CISS 2024 conference.
Nov 16, 2023 Paper on mean-field approximations for stochastic processes on networks published in the SIAM Journal on Control and Optimization (SICON). Joint work with Soummya Kar.
Sep 19, 2023 New paper on the average-case and smoothed complexity of graph isomorphism. Joint work with Miki Rácz and Julia Gaudio.

selected publications

2024

  1. COLT 2024
    Finding Super-spreaders in Network Cascades
    Elchanan Mossel, and Anirudh Sridhar
    Proceedings of the Conference on Learning Theory, Jul 2024

2023

  1. SICON
    Mean-field Approximations for Stochastic Population Processes with Heterogeneous Interactions
    Anirudh Sridhar, and Soummya Kar
    SIAM Journal on Control and Optimization, Nov 2023
  2. PNAS
    Spreading Processes with Mutations over Multi-Layer Networks
    Mansi Sood, Anirudh Sridhar, Rashad Eletreby, Chai Wah Wu, Simon A. Levin, H. Vincent Poor, and Osman Yagan
    Proceedings of the National Academy of Sciences, Jun 2023
  3. IEEE-IT
    Quickest Inference of Network Cascades with Noisy Information
    Anirudh Sridhar, and H. Vincent Poor
    IEEE Transactions on Information Theory, Apr 2023

2022

  1. COLT 2022
    Exact Community Recovery in Correlated Stochastic Block Models
    Julia Gaudio, Miklós Z. Rácz, and Anirudh Sridhar
    In Proceedings of the 35th Annual Conference on Learning Theory, Jul 2022