Sambit Mishra

Research

Reliable causal structure, learned at scale.

My research lives at the intersection of causal inference, probabilistic graphical models, and continuous optimization. The unifying question: when can causal structure be recovered from data — efficiently, and with guarantees — and when can it not?

§ 01

Themes.

/ 01

Identifiability theory

Characterizing when causal structure can be uniquely recovered from observational and interventional data, and turning those identifiability conditions into efficient discovery algorithms for identifiable directed acyclic graphs.

/ 02

Scalable causal discovery

Continuous-optimization formulations of structure learning that replace combinatorial search over DAGs with differentiable acyclicity constraints, enabling GPU-accelerated estimation on high-dimensional, mixed-distribution data.

/ 03

Bounds under partial identifiability

Variance bounds and lowest-variance estimators for the non- and partially-identifiable regimes — quantifying what can still be learned about causal structure when it is not uniquely determined.

/ 04

Optimized soft interventions

Intervention-selection policies that maximize identifiability gain per experiment, reducing the number and cost of interventions needed to recover causal structure.

§ 02

Publications.

Peer-reviewed work in causal inference and wireless communications. For the most up-to-date list see my Google Scholar profile.

  1. [01]

    ICASSP 2026

    Barcelona, pp. 6196–6200

    Learning to Intervene: Optimized Soft Intervention Selection for Causal Discovery

    C. Peng, S. Mishra, U. Mitra

    Proposes a learning-based framework for selecting soft interventions that improves causal-discovery efficiency and reduces experimental cost.

    doi: 10.1109/ICASSP55912.2026.11460954
  2. [02]

    IEEE Transactions on Green Communications and Networking

    Vol. 10, pp. 1433–1445, 2026

    SER-Optimized Multi-Level ASK Modulations for RIS-Assisted Communications With Energy- and Sign-Based Noncoherent Reception

    S. Mishra, S. P. Dash, G. C. Alexandropoulos

    Investigates one- and two-sided ASK modulations in noncoherent SISO systems assisted by an RIS, proposing novel energy- and sign-based receiver structures.

    doi: 10.1109/TGCN.2025.3633182
  3. [03]

    IEEE Wireless Communications Letters

    Vol. 15, pp. 300–304, 2026

    Error Analysis With Optimal Receiver and Multi-Level ASK for RIS-Assisted Noncoherent Wireless System

    S. Mishra, S. P. Dash

    Considers RIS-aided wireless communication with one-sided ASK and an optimal noncoherent maximum-likelihood detection rule.

    doi: 10.1109/LWC.2025.3624154

§ 03

Earlier projects.

Fully-analog audio system with active noise cancellation

Aug 2024 — Oct 2024

Electronic System Design Lab, IIT Bhubaneswar

  • ▹Designed a noise-resilient audio system using a fully analog implementation of active noise cancellation.
  • ▹Performed circuit simulations in Multisim and laid out PCBs in KiCAD.

Collaborate

Working on a related question?

I’m always glad to chat about causal discovery, identifiability, or scalable structure-learning methods.

sambitmi@usc.edu