Jiaqi Yang

Jiaqi Yang

Hi! I am a first-year Ph.D. student in Computer Science at the University of California, Berkeley, and I am with the Berkeley Artificial Intelligence Research (BAIR) Lab. Previously, I received my B.E. in Computer Science and Technology (Yao Class) and B.S. in Pure and Applied Mathematics (For Second Bachelor Degree) from Tsinghua University in 2021.

Contact: yangjq17 ᴀᴛ gmail.com; yjq ᴀᴛ berkeley.edu

Links: Google Scholar / DBLP / arXiv

Publications

  1. Going Beyond Linear RL: Sample Efficient Neural Function Approximation
    Baihe Huang*, Kaixuan Huang*, Sham M. Kakade*, Jason D. Lee*, Qi Lei*, Runzhe Wang*, Jiaqi Yang*
    Preprint
  2. Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
    Baihe Huang*, Kaixuan Huang*, Sham M. Kakade*, Jason D. Lee*, Qi Lei*, Runzhe Wang*, Jiaqi Yang*
    Preprint
  3. Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
    Kefan Dong, Jiaqi Yang, Tengyu Ma
    Preprint
  4. Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP
    Zihan Zhang*, Jiaqi Yang*, Xiangyang Ji, Simon S. Du
    Preprint
  5. Fully Gap-Dependent Bounds for Multinomial Logit Bandit
    Jiaqi Yang
    International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
  6. Impact of Representation Learning in Linear Bandits
    Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du
    International Conference on Learning Representations (ICLR) 2021
  7. Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Design
    Yufei Ruan*, Jiaqi Yang*, Yuan Zhou*
    ACM Symposium on Theory of Computing (STOC) 2021

Selected Award