Rama Krishnamurthy

(First name pronunciation)

PhD candidate,
Courant Institute of Mathematical Sciences,
New York University.

Email- rk4312@nyu.edu

About Me

News

Welcome!
I am a PhD candidate in Computer Science at Courant Institute of Mathematical Sciences @ New York University (NYU) since Fall 2022.

My research interests are in methodological and collaborative aspects of Multi-Agentic AI systems, with my academic interests broadly in the Machine Learning fields of Online Learning, Bandits, Game Theory, and Reinforcement Learning. My work is also sometimes motivated by Fairness in algorithms.

At NYU, I am advised by Lakshmi Subramanian; I was a Visiting Researcher at Meta in the FAIR team (2023-2025) mentored by Max Nickel in the initial part of my PhD.

Before my PhD, I was an M. Tech (by Research) student of Computer Science (CSA) at the Indian Institute of Science (IISc), Bangalore, where I am happy to have been advised by Rahul Saladi and also to have collaborated with Siddharth Barman and Aditya Gopalan.
I also have extensive software-engineering experience with Microsoft.

[Sep 2026] - My (first ever!) single-author paper `On Impact of Extra Information in Bandit Feedback' has been accepted to NeurIPS .
---I'll present my paper in Atlanta on December 11th at 10am in Hall C1.
[Sep 2026] - Giving a Job Talk at INFORMS Annual Meeting in San Fransisco CA on November 1st at 8.30am!
[Jan 2026] - Our paper `Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach' has been accepted at AISTATS 2026 as an Oral presentation (Top 8 out of ~2100 papers)
[Oct 2025] - Presenting our work on 'Creator Incentives in Recommender Systems' at INFORMS Annual Meeting in Atlanta GA!
[Aug 2025] - Presented our work on "On Slowly-varying Non-stationary Bandits" at RLC 2025 in Edmonton, Canada.
[July 2024] - Presented our work on "Collaborative Learning under Strategic Behavior: Mechanisms for Eliciting Feedback in Principal-Agent Bandit Games" [Open Review] at the Agentic Markets Workshop at ICML 2024 in Vienna.

Publications

[5] On the Impact of Extra Information In Bandit Learning: More is Not Always Merrier
Rama Krishnamurthy
at 40th Conference on Neural Information Processing Systems, NeurIPS 2026 [Link]
[4] Collaborative Learning under Strategic Behavior: Mechanisms for Eliciting Feedback in Principal-Agent Bandit Games
Rama Krishnamurthy, Arpit Agarwal, Lakshmi Subramanian, Max Nickel
at 3rd Reinforcement Learning Conference, RLC 2026 [OpenReview]
[3] Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
Rama Krishnamurthy, Arpit Agarwal, Lakshmi Subramanian, Max Nickel
at 29th Conference on Artificial Intelligence and Statistics, AISTATS 2026 [OpenReview] as Oral Presentation (Top 8/~2000 submissions)
[2] On Slowly-varying Non-stationary Bandits
Rama Krishnamurthy and Aditya Gopalan
at 2nd Reinforcement Learning Conference, RLC 2025 [OpenReview] [arXiv]
[1] Optimal Algorithms for Range Searching over Multi-Armed Bandits
Siddharth Barman, Rama Krishnamurthy, and Saladi Rahul
at 30th International Joint Conference on Artificial Intelligence, IJCAI 2021 [arXiv]
also presented virtually at 5th Workshop on Geometry and Machine Learning (WaGoML), at SoCG-21 [slides]
[*] First-Order Increase in UCB Regret under Extra Information
Rama Krishnamurthy
(under submission.)

Teaching and Service

Teaching Assistance
- TA for Design and Analysis of Algorithms (E0 225 @ IISc), Fall 2021 (Instructors: Rahul Saladi & Siddharth Barman)
- TA for Game Theory & Mechanism Design (E1 254 @ IISc), Spring 2022. (Instructor: Y. Narahari)
- Recitation Section Leader for Basic Algorithms (CSCI-UA.0310 @ NYU), Fall 2025. (Instructor: Oded Regev)
- Recitation Section Leader for Basic Algorithms (CSCI-UA.0310 @ NYU), Spring 2026. (Instructor: Nir Bitansky)
- Recitation Section Leader for Basic Algorithms (CSCI-UA.0310 @ NYU), Fall 2026. (Instructor: Ernest Davis)
Voluntary Peer Reviewer for ML conferences
- AISTATS (2022 Top Reviewer - 10% ; 2024)
- NeurIPS (2023 Top Reviewer )
- ICML (2024, 2026 Gold Reviewer)

Industry Experience

Software Development Engineer with Microsoft, Hyderabad (2015-19) : Team STCI (Search Technology Center - India)
- - Bing Local Content - Created faster pipelines for time-critical offers data. Developed and automated an E-E workflow for Healthcare experience for GB market with NHS data. Owned the Review Pipeline, developed multiple features, served as a POC for the entire Review experience. Shipped a richer answer (mobile and desktop) for Chain queries with curated data.
  - Bing Local UX - Built user experiences in bing.com for the following: LinkedIn professionals experience; Pulse feedback module (experimental); a major revamped Task-pane answer for GB market; a Refreshed Hours of Operations module.

Visiting Researcher with Meta, New York City (2023-25) : Team FAIR (Fundamental AI Research)
- - Worked with Max Nickel and Arpit Agarwal on research problems in the space of multi-agent learning in the presence of strategic agents, motivated by real world recommender systems.

Page updated

Google Sites

Report abuse