Anand Kumar Siththaranjan

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2025-221

December 19, 2025

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-221.pdf

Information asymmetries, where some agents have information that others do not have, are ubiquitous in social interactions. This poses a challenge to social planners, whose role is to implement outcomes that are beneficial to the constituents they represent. However, planners require information about the state of the world, agents' preferences, and how they make decisions. Hence to bridge this informational gap they must leverage learning. I study three approaches to learning, which include data-driven learning, communication and Bayesian learning, and the design of incentives. The key methodological tools lie in leveraging optimization theory to characterize optimal solutions, game theory to model the role of incentives and strategic behaviour, and market design to formulate desirable properties of solutions and how to implement them. These approaches are applied to different environments, including the development of robust large language models, economic interactions between buyers and sellers, and the design of paired organ exchange systems.

Advisors: Stuart J. Russell and Claire Tomlin

---

BibTeX citation:

@phdthesis{Siththaranjan:EECS-2025-221,
    Author= {Siththaranjan, Anand Kumar},
    Title= {Bridging Information Asymmetries Through Learning},
    School= {EECS Department, University of California, Berkeley},
    Year= {2025},
    Month= {Dec},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-221.html},
    Number= {UCB/EECS-2025-221},
    Abstract= {Information asymmetries, where some agents have information that others do not have, are ubiquitous in social interactions. This poses a challenge to social planners, whose role is to implement outcomes that are beneficial to the constituents they represent. However, planners require information about the state of the world, agents' preferences, and how they make decisions. Hence to bridge this informational gap they must leverage learning. I study three approaches to learning, which include data-driven learning, communication and Bayesian learning, and the design of incentives. The key methodological tools lie in leveraging optimization theory to characterize optimal solutions, game theory to model the role of incentives and strategic behaviour, and market design to formulate desirable properties of solutions and how to implement them. These approaches are applied to different environments, including the development of robust large language models, economic interactions between buyers and sellers, and the design of paired organ exchange systems.},
}

EndNote citation:

%0 Thesis
%A Siththaranjan, Anand Kumar 
%T Bridging Information Asymmetries Through Learning
%I EECS Department, University of California, Berkeley
%D 2025
%8 December 19
%@ UCB/EECS-2025-221
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-221.html
%F Siththaranjan:EECS-2025-221