Yinan Li

I am a Ph.D. student in Computer Science at the University of Arizona, where I am fortunate to be advised by Prof. Kwang-Sung Jun.

My research focuses on the theoretical foundations of machine learning, particularly statistical learning theory and sequential decision-making. I am interested in understanding how to learn reliably in the presence of noise and model misspecification, and how to make efficient decisions with limited data. I am also interested in theoretical questions arising from modern language models.

I am currently on the job market for research positions in academia and industry.

Outside of research, I am an avid pianist and have been playing since childhood. I also love hitting the gym and trying out different kinds of workouts!

Portrait of Yinan Li

Publications

  1. Halve-Then-Greedy: Adaptive Sampling for Posterior Success with Near-Optimal Instance Dependence

    Yinan Li, Kwang-Sung Jun, Kapilan Balagopalan, Tuan Nguyen, Yao Zhao, Abbas Zaidi, Houssam Nassif

    Preprint, 2026 [Paper]

  2. Sign Betting for Misspecified Regression: Variance Adaptivity and Optimal Approximation

    Yinan Li, Han Han, Kwang-Sung Jun

    Preprint, 2026 [Paper]

  3. ε-Good Action Identification in Fixed-Budget Monte Carlo Tree Search

    Yinan Li, Tuan Nguyen, Kwang-Sung Jun

    Advances in Neural Information Processing Systems (NeurIPS), 2026 [Paper]

  4. Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

    Kapilan Balagopalan*, Yinan Li*, Yao Zhao, Tuan Ngo Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun

    International Conference on Machine Learning (ICML), 2026 [Paper]

    * Equal contribution.

  5. Second-Order Bounds for [0, 1]-Valued Regression via Betting Loss

    Yinan Li, Sungjoon Yoon, Ethan Huang, Kwang-Sung Jun

    Conference on Learning Theory (COLT), 2026 [Paper]

  6. Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach

    Yinan Li, Chicheng Zhang

    International Conference on Artificial Intelligence and Statistics (AISTATS), 2024 [Paper]

  7. Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov Noise

    Chicheng Zhang, Yinan Li

    Conference on Learning Theory (COLT), 2021 [Paper]