Karthikeyan Shanmugam

About

Karthikeyan Shanmugam is currently a Research Scientist at Google DeepMind India in the Machine Learning and Optimization Team. Previously, he was a Research Staff Member with the IBM Research AI, NY during the period 2017-2022 and a Herman Goldstine Postdoctoral Fellow at IBM Research, NY in the period 2016-2017. He obtained his Ph.D. in ECE from UT Austin in 2016. He is a recipient of the IBM Corporate Technical Award in 2021 for his work on Trustworthy AI. His current research focus is on causal inference, online learning, representation learning and Foundation Models in Machine Learning. He is also interested in Information Theory and Coding Theory.

Employment

• Google Deepmind India Research Scientist
  2024 - Present
• Google (India) Research Scientist
  2022 - 2024
• IBM Research - Thomas J. Watson Research Center Research Staff Member
  2017 - 2022

Education

• The University of Texas at Austin Doctor of Philosophy
  2013 - 2016
• University of Southern California Master of Science
  2010 - 2012
• Indian Institute of Technology Madras Master of Technology
  2005 - 2010
• Indian Institute of Technology Madras Bachelor of Technology
  2005 - 2010

Projects & Funding

Projects & funding information is unavailable.

Publications (138)

• Online Bidding under RoS Constraints without Knowing the Value
  2025 DOI: 10.1145/3696410.3714734
  +Save
• Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes
  ACM Transactions on Modeling and Performance Evaluation of Computing Systems 2024 DOI: 10.1145/3680279
  +Save
• A Lyapunov Theory for Finite-Sample Guarantees of Markovian Stochastic Approximation
  Operations Research 2024 DOI: 10.1287/opre.2022.0249
  +Save
• Fault Injection Based Interventional Causal Learning for Distributed Applications
  Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances … 2023 DOI: 10.1609/aaai.v37i13.26868
  +Save
• Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
  CoRR 2023 DOI: 10.48550/arXiv.2306.11008
  +Save
• Identifiability Guarantees for Causal Disentanglement from Soft Interventions
  CoRR 2023 DOI: 10.48550/arXiv.2307.06250
  +Save
• InfoNCE Loss Provably Learns Cluster-Preserving Representations
  The Thirty Sixth Annual Conference on Learning Theory, COLT 2023, 12-15 July 2023, Bangalore, India 2023
  +Save
• InfoNCE Loss Provably Learns Cluster-Preserving Representations
  CoRR 2023 DOI: 10.48550/arXiv.2302.07920
  +Save
• Optimal Algorithms for Latent Bandits with Cluster Structure
  International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain 2023
  +Save
• Optimal Algorithms for Latent Bandits with Cluster Structure
  CoRR 2023 DOI: 10.48550/arXiv.2301.07040
  +Save