Vinod Raman

Vinod Raman

Research Scientist @ Google DeepMind

I’m a Research Scientist at Google DeepMind working on improving Gemini’s fundamental capabilities for retrieval and ranking.

I completed my Ph.D. in Statistics at the University of Michigan in 2025, where I was fortunate to be advised by Ambuj Tewari. My Ph.D. was graciously supported by the National Science Foundation Graduate Research Fellowship (NSF GRFP) and the 2025 Apple Scholars in AI/ML PhD Fellowship. Prior to my Ph.D, I double-majored in Computer Science and Chemical Engineering also at UofM where I worked with Mahdi Cheraghchi, Sindhu Kutty, and Andrej Lenert.

My research interests lie in the Foundations of Machine Learning. During my Ph.D, I worked on various topics in learning theory, including online learning, adversarial robustness, differential privacy, and language generation, among other things. More recently, I am interested in post-training for large language models, particularly reasoning and adaptive compute.

Apart from research and work, I am a fan of bodybuilding and actively keep up with the Mr. Olympia.

Preprints

  1. On Generation in Metric Spaces
    with Jiaxun Li , Ambuj Tewari
    Preprint, 2026.
  2. Estimating the (Un)seen: Sample-dependent Mass Estimation PDF
    with Vitaly Feldman, Satyen Kale, Kunal Talwar, and Ambuj Tewari
    Preprint, 2025.
  3. Transductive and Learning-Augmented Online Regression PDF
    with Shenghao Xie , Samson Zhou
    In Submission, 2025.
  4. Online Boosting for Multilabel Ranking with Top-k Feedback PDF
    with Daniel T. Zhang, Young Hun Jung, Ambuj Tewari
    Preprint, 2020.

In Submission

  1. Optimal Stopping vs Best-of-N for Inference Time Optimization PDF
    with Yusuf Kalayci , Shaddin Dughmi
    In Submission, 2026.
  2. AdaBoN: Adaptive Best-of-N Alignment PDF
    with Hilal Asi , Satyen Kale
    In Submission, 2026.
  3. AI-rithmetic
    with Alex Bie, Travis Dick, Alex Kulesza, Prabhakar Raghavan, Sergei Vassilvitskii
    In Submission, 2026.

Publications

Language Generation

  1. Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation PDF
    with Seamus Somerstep , Unique Subedi , Yuekai Sun
    Conference on Artificial Intelligence and Statistics (AISTATS), 2026.
    also at Conference on the Mathematical Theory of Deep Neural Networks (DeepMath), 2025.
  2. Generation through the lens of learning theory PDF
    with Jiaxun Li , Ambuj Tewari
    Conference on Learning Theory (COLT), 2025.
  3. Representative Language Generation PDF
    with Charlotte Peale , Omer Reingold
    International Conference on Machine Learning (ICML), 2025.
  4. Generation from Noisy Examples PDF
    with Ananth Raman
    International Conference on Machine Learning (ICML), 2025.

Differential Privacy

  1. Missing Mass for Differentially Private Domain Discovery
    with Matthew Joseph , Travis Dick
    International Conference on Learning Representations (ICLR), 2026.
  2. Tracking the Best Expert Privately PDF
    with Hilal Asi , Aadirupa Saha
    International Conference on Machine Learning (ICML), 2025.
  3. Faster Rates for Private Adversarial Bandits PDF
    with Hilal Asi, Kunal Talwar
    International Conference on Machine Learning (ICML), 2025.

Beyond Worst-case Guarantees for Learning

  1. Online Classification with Predictions PDF
    with Ambuj Tewari
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
  2. Smoothed Online Classification can be Harder than Batch Classification PDF
    with Unique Subedi, Ambuj Tewari
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
  3. Multiclass Transductive Online Learning Spotlight PDF
    with Steve Hanneke, Amirreza Shaeiri, Unique Subedi
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
  4. On Proper Learnability between Average- and Worst-case Robustness PDF
    with Unique Subedi, Ambuj Tewari
    Conference on Neural Information Processing Systems (NeurIPS), 2023.

Online Learning

  1. The Complexity of Sequential Prediction in Dynamical Systems Oral PDF
    with Unique Subedi, Ambuj Tewari
    Conference on Learning for Dynamics and Control (L4DC), 2025.
  2. A Unified Theory of Supervised Online Learnability Outstanding PaperPDF
    with Unique Subedi, Ambuj Tewari
    Conference on Algorithmic Learning Theory (ALT), 2025.
  3. Online Learning with Set-Valued Feedback PDF
    with Unique Subedi, Ambuj Tewari
    Conference on Learning Theory (COLT), 2024.
  4. Online Infinite-Dimensional Regression: Learning Linear Operators PDF
    with Unique Subedi, Ambuj Tewari
    Conference on Algorithmic Learning Theory (ALT), 2024.
  5. Multiclass Online Learning and Uniform Convergence PDF
    with Steve Hanneke, Shay Moran, Unique Subedi, Ambuj Tewari
    Conference on Learning Theory (COLT), 2023.
  6. Online Agnostic Multiclass Boosting PDF
    with Ambuj Tewari
    Conference on Neural Information Processing Systems (NeurIPS), 2022.

Partial Feedback

  1. Apple Tasting: Combinatorial Dimensions and Minimax Rates PDF
    with Ananth Raman , Unique Subedi, Ambuj Tewari
    Conference on Learning Theory (COLT), 2024.
  2. Multiclass Online Learnability under Bandit Feedback PDF
    with Ananth Raman , Unique Subedi, Idan Mehalel, Ambuj Tewari
    Conference on Algorithmic Learning Theory (ALT), 2024.

Multioutput Learning

  1. A Characterization of Multioutput Learnability PDF
    with Unique Subedi, Ambuj Tewari
    Journal of Machine Learning Research (JMLR), 2024.
  2. On the Learnability of Multilabel Ranking SpotlightPDF
    with Unique Subedi, Ambuj Tewari
    Conference on Neural Information Processing Systems (NeurIPS), 2023.

Other

  1. Design of thermophotovoltaics for tolerance of parasitic absorption PDF
    with Tobias Burger, Andrej Lenert
    Optics Express, 2019.