PPaperPicks

Peng Zhao

Nanjing University, National Key Laboratory for Novel Software Technology, Cjina

19 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-7925-8255 ↗

Venues

NeurIPS ×8ICML ×6COLT ×2AAAI ×1AISTATS ×1SIGMOD ×1

Frequent coauthors

Zhi-Hua Zhou
×14
Long-Fei Li
×5
Yu-Hu Yan
×4
Yu-Jie Zhang
×4
Jing Wang
×3
Yu-Yang Qian
×3
Yuheng Zhao
×2
Masashi Sugiyama
×2
Yi-Han Wang
×1
Hanyan Yin
×1
Dongxie Wen
×1
Jiajun Li
×1

Papers

  1. A simple, optimal and efficient algorithm for online exp-concave optimization
    COLT 2026 ·
    Yi-Han Wang
    , Peng Zhao,
    Zhi-Hua Zhou
  2. AeroSketch: Near-Optimal Time Matrix Sketch Framework for Persistent, Sliding Window, and Distributed Streams
    SIGMOD 2026 ·
    Hanyan Yin
    ,
    Dongxie Wen
    ,
    Jiajun Li
    ,
    Zhewei Wei
    ,
    Xiao Zhang
    , Peng Zhao,
    Zhi-Hua Zhou
  3. Gradient-Variation Regret Bounds for Unconstrained Online Learning
    COLT 2026 ·
    Yuheng Zhao
    ,
    Andrew Jacobsen
    ,
    Nicolò Cesa-Bianchi
    , Peng Zhao
  4. Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
    NeurIPS 2025 ·
    Yuheng Zhao
    ,
    Yu-Hu Yan
    ,
    Kfir Y. Levy
    , Peng Zhao
  5. Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
    ICML 2025 ·
    Jing Wang
    ,
    Yu-Jie Zhang
    , Peng Zhao,
    Zhi-Hua Zhou
  6. Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
    ICML 2025 ·
    Yu-Jie Zhang
    , Peng Zhao,
    Masashi Sugiyama
  7. Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
    NeurIPS 2025 ·
    Yu-Hu Yan
    , Peng Zhao,
    Zhi-Hua Zhou
  8. Provably Efficient Online RLHF with One-Pass Reward Modeling
    NeurIPS 2025 ·
    Long-Fei Li
    ,
    Yu-Yang Qian
    , Peng Zhao,
    Zhi-Hua Zhou
  9. TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
    ICML 2025 ·
    Yu-Yang Qian
    ,
    Yuan-Ze Xu
    ,
    Zhen-Yu Zhang
    , Peng Zhao,
    Zhi-Hua Zhou
  10. A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
    NeurIPS 2024 ·
    Yu-Hu Yan
    , Peng Zhao,
    Zhi-Hua Zhou
  11. Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation
    AAAI 2024 ·
    Long-Fei Li
    , Peng Zhao,
    Zhi-Hua Zhou
  12. Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation
    ICML 2024 ·
    Yu-Yang Qian
    , Peng Zhao,
    Yu-Jie Zhang
    ,
    Masashi Sugiyama
    ,
    Zhi-Hua Zhou
  13. Gradient-Variation Online Learning under Generalized Smoothness
    NeurIPS 2024 ·
    Yan-Feng Xie
    , Peng Zhao,
    Zhi-Hua Zhou
  14. Handling Heterogeneous Curvatures in Bandit LQR Control
    ICML 2024 ·
    Yu-Hu Yan
    ,
    Jing Wang
    , Peng Zhao
  15. Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
    AISTATS 2024 ·
    Long-Fei Li
    , Peng Zhao,
    Zhi-Hua Zhou
  16. Learning with Adaptive Resource Allocation
    ICML 2024 ·
    Jing Wang
    ,
    Miao Yu
    , Peng Zhao,
    Zhi-Hua Zhou
  17. Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
    NeurIPS 2024 ·
    Long-Fei Li
    , Peng Zhao,
    Zhi-Hua Zhou
  18. Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
    NeurIPS 2024 ·
    Long-Fei Li
    ,
    Yu-Jie Zhang
    , Peng Zhao,
    Zhi-Hua Zhou
  19. Universal Online Convex Optimization with 1 Projection per Round
    NeurIPS 2024 ·
    Wenhao Yang
    ,
    Yibo Wang
    , Peng Zhao,
    Lijun Zhang