Peng Zhao

100 papers A* 35A 7Journal 56Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
AeroSketch: Near-Optimal Time Matrix Sketch Framework for Persistent, Sliding Window, and Distributed Streams.
CoRR
Hanyan Yin, Dongxie Wen, Jiajun Li, Zhewei Wei, Xiao Zhang, Peng Zhao, Zhi-Hua Zhou
2026 J jnl
Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer.
CoRR
Yan-Feng Xie, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2026 J jnl
Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations.
CoRR
Hang Yu, Yu-Hu Yan, Peng Zhao
2026 J jnl
Internalizing Agency from Reflective Experience.
CoRR
Rui Ge, Yichao Fu, Yuyang Qian, Junda Su, Yiming Zhao, Peng Zhao, Hao Zhang
2026 J jnl
Revisiting Weighted Strategy for Non-Stationary Parametric Bandits and MDPs.
IEEE Trans. Inf. Theory
Jing Wang, Peng Zhao, Zhi-Hua Zhou
2026 J jnl
Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs.
CoRR
Jing Wang, Peng Zhao, Zhi-Hua Zhou
2026 J jnl
When Drafts Evolve: Speculative Decoding Meets Online Learning.
CoRR
Yu-Yang Qian, Hao-Cong Wu, Yichao Fu, Hao Zhang, Peng Zhao
2026 J jnl
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation.
CoRR
Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang
2025 J jnl
A Simple, Optimal and Efficient Algorithm for Online Exp-Concave Optimization.
CoRR
Yi-Han Wang, Peng Zhao, Zhi-Hua Zhou
2025 J jnl
Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization.
CoRR
Peng Zhao, Yu-Hu Yan, Hang Yu, Zhi-Hua Zhou
2025 J jnl
Efficient Methods for Non-stationary Online Learning.
J. Mach. Learn. Res.
Peng Zhao, Yan-Feng Xie, Lijun Zhang, Zhi-Hua Zhou
2025 J jnl
Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness.
CoRR
Yuheng Zhao, Yu-Hu Yan, Kfir Yehuda Levy, Peng Zhao
2025 J jnl
Handling New Class in Online Label Shift.
IEEE Trans. Knowl. Data Eng.
Yu-Yang Qian, Yong Bai, Zhen-Yu Zhang, Peng Zhao, Zhi-Hua Zhou
2025 A* conf
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update.
ICML
Jing Wang, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2025 J jnl
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update.
CoRR
Jing Wang, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2025 J jnl
Learning Objective Adaptation by Correlation-Based Model Reuse.
IEEE Trans. Neural Networks Learn. Syst.
Lanjihong Ma, Yao-Xiang Ding, Peng Zhao, Zhi-Hua Zhou
2025 A* conf
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability.
ICML
Yu-Jie Zhang, Peng Zhao, Masashi Sugiyama
2025 J jnl
Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality.
CoRR
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2025 J jnl
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits.
CoRR
Long-Fei Li, Yu-Yang Qian, Peng Zhao, Zhi-Hua Zhou
2025 A* conf
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree.
ICML
Yu-Yang Qian, Yuan-Ze Xu, Zhen-Yu Zhang, Peng Zhao, Zhi-Hua Zhou
2025 J jnl
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree.
CoRR
Yu-Yang Qian, Yuan-Ze Xu, Zhen-Yu Zhang, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
A Simple and Optimal Approach for Universal Online Learning with Gradient Variations.
NeurIPS
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization.
J. Mach. Learn. Res.
Peng Zhao, Yu-Jie Zhang, Lijun Zhang, Zhi-Hua Zhou
2024 A* conf
Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation.
AAAI
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation.
ICML
Yu-Yang Qian, Peng Zhao, Yu-Jie Zhang, Masashi Sugiyama, Zhi-Hua Zhou
2024 J jnl
Exploratory machine learning with unknown unknowns.
Artif. Intell.
Peng Zhao, Jia-Wei Shan, Yu-Jie Zhang, Zhi-Hua Zhou
2024 A* conf
Gradient-Variation Online Learning under Generalized Smoothness.
NeurIPS
Yan-Feng Xie, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Gradient-Variation Online Learning under Generalized Smoothness.
CoRR
Yan-Feng Xie, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
Handling Heterogeneous Curvatures in Bandit LQR Control.
ICML
Yu-Hu Yan, Jing Wang, Peng Zhao
2024 A conf
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition.
AISTATS
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition.
CoRR
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
Learning with Adaptive Resource Allocation.
ICML
Jing Wang, Miao Yu, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Learning with Asynchronous Labels.
ACM Trans. Knowl. Discov. Data
Yu-Yang Qian, Zhen-Yu Zhang, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs.
NeurIPS
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs.
CoRR
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization.
J. Mach. Learn. Res.
Sijia Chen, Yu-Jie Zhang, Wei-Wei Tu, Peng Zhao, Lijun Zhang
2024 A* conf
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation.
NeurIPS
Long-Fei Li, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2024 J jnl
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation.
CoRR
Long-Fei Li, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2024 A* conf
Universal Online Convex Optimization with 1 Projection per Round.
NeurIPS
Wenhao Yang, Yibo Wang, Peng Zhao, Lijun Zhang
2024 J jnl
Universal Online Convex Optimization with 1 Projection per Round.
CoRR
Wenhao Yang, Yibo Wang, Peng Zhao, Lijun Zhang
2023 J jnl
Adapting to Continuous Covariate Shift via Online Density Ratio Estimation.
CoRR
Yu-Jie Zhang, Zhen-Yu Zhang, Peng Zhao, Masashi Sugiyama
2023 A conf
Beyond Performative Prediction: Open-environment Learning with Presence of Corruptions.
AISTATS
Jia-Wei Shan, Peng Zhao, Zhi-Hua Zhou
2023 A* conf
Dynamic Regret of Adversarial Linear Mixture MDPs.
NeurIPS
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
2023 J jnl
Efficient Methods for Non-stationary Online Learning.
CoRR
Peng Zhao, Yan-Feng Xie, Lijun Zhang, Zhi-Hua Zhou
2023 A* conf
Fast Rates in Time-Varying Strongly Monotone Games.
ICML
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2023 A* conf
Handling New Class in Online Label Shift.
ICDM
Yu-Yang Qian, Yong Bai, Zhen-Yu Zhang, Peng Zhao, Zhi-Hua Zhou
2023 J jnl
Non-stationary Online Learning with Memory and Non-stochastic Control.
J. Mach. Learn. Res.
Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, Zhi-Hua Zhou
2023 J jnl
Online Non-stochastic Control with Partial Feedback.
J. Mach. Learn. Res.
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2023 A* conf
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization.
ICML
Sijia Chen, Wei-Wei Tu, Peng Zhao, Lijun Zhang
2023 J jnl
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization.
CoRR
Sijia Chen, Wei-Wei Tu, Peng Zhao, Lijun Zhang
2023 A conf
Revisiting Weighted Strategy for Non-stationary Parametric Bandits.
AISTATS
Jing Wang, Peng Zhao, Zhi-Hua Zhou
2023 J jnl
Revisiting Weighted Strategy for Non-stationary Parametric Bandits.
CoRR
Jing Wang, Peng Zhao, Zhi-Hua Zhou
2023 A* conf
Stochastic Approximation Approaches to Group Distributionally Robust Optimization.
NeurIPS
Lijun Zhang, Peng Zhao, Zhen-Hua Zhuang, Tianbao Yang, Zhi-Hua Zhou
2023 J jnl
Stochastic Approximation Approaches to Group Distributionally Robust Optimization.
CoRR
Lijun Zhang, Peng Zhao, Tianbao Yang, Zhi-Hua Zhou
2023 A* conf
Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach.
NeurIPS
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2023 J jnl
Universal Online Learning with Gradual Variations: A Multi-layer Online Ensemble Approach.
CoRR
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2022 A* conf
Adapting to Online Label Shift with Provable Guarantees.
NeurIPS
Yong Bai, Yu-Jie Zhang, Peng Zhao, Masashi Sugiyama, Zhi-Hua Zhou
2022 J jnl
Adapting to Online Label Shift with Provable Guarantees.
CoRR
Yong Bai, Yu-Jie Zhang, Peng Zhao, Masashi Sugiyama, Zhi-Hua Zhou
2022 A* conf
Adaptive Bandit Convex Optimization with Heterogeneous Curvature.
COLT
Haipeng Luo, Mengxiao Zhang, Peng Zhao
2022 J jnl
Adaptive Bandit Convex Optimization with Heterogeneous Curvature.
CoRR
Haipeng Luo, Mengxiao Zhang, Peng Zhao
2022 A* conf
Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits.
COLT
Haipeng Luo, Mengxiao Zhang, Peng Zhao, Zhi-Hua Zhou
2022 J jnl
Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits.
CoRR
Haipeng Luo, Mengxiao Zhang, Peng Zhao, Zhi-Hua Zhou
2022 A* conf
Dynamic Regret of Online Markov Decision Processes.
ICML
Peng Zhao, Longfei Li, Zhi-Hua Zhou
2022 J jnl
Dynamic Regret of Online Markov Decision Processes.
CoRR
Peng Zhao, Longfei Li, Zhi-Hua Zhou
2022 A* conf
Efficient Methods for Non-stationary Online Learning.
NeurIPS
Peng Zhao, Yan-Feng Xie, Lijun Zhang, Zhi-Hua Zhou
2022 J jnl
Improving Deep Forest by Screening.
IEEE Trans. Knowl. Data Eng.
Ming Pang, Kai Ming Ting, Peng Zhao, Zhi-Hua Zhou
2022 J jnl
Learning From Incomplete and Inaccurate Supervision.
IEEE Trans. Knowl. Data Eng.
Zhen-Yu Zhang, Peng Zhao, Yuan Jiang, Zhi-Hua Zhou
2022 A* conf
No-Regret Learning in Time-Varying Zero-Sum Games.
ICML
Mengxiao Zhang, Peng Zhao, Haipeng Luo, Zhi-Hua Zhou
2022 J jnl
No-Regret Learning in Time-Varying Zero-Sum Games.
CoRR
Mengxiao Zhang, Peng Zhao, Haipeng Luo, Zhi-Hua Zhou
2022 A conf
Non-stationary Online Learning with Memory and Non-stochastic Control.
AISTATS
Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou
2021 J jnl
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization.
CoRR
Peng Zhao, Yu-Jie Zhang, Lijun Zhang, Zhi-Hua Zhou
2021 J jnl
Bandit Convex Optimization in Non-stationary Environments.
J. Mach. Learn. Res.
Peng Zhao, Guanghui Wang, Lijun Zhang, Zhi-Hua Zhou
2021 J jnl
Distribution-Free One-Pass Learning.
IEEE Trans. Knowl. Data Eng.
Peng Zhao, Xinqiang Wang, Siyu Xie, Lei Guo, Zhi-Hua Zhou
2021 A* conf
Exploratory Machine Learning with Unknown Unknowns.
AAAI
Peng Zhao, Yu-Jie Zhang, Zhi-Hua Zhou
2021 — conf
Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functions.
L4DC
Peng Zhao, Lijun Zhang
2021 J jnl
Non-stationary Linear Bandits Revisited.
CoRR
Peng Zhao, Lijun Zhang
2021 J jnl
Non-stationary Online Learning with Memory and Non-stochastic Control.
CoRR
Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou
2021 A* conf
Storage Fit Learning with Feature Evolvable Streams.
AAAI
Bo-Jian Hou, Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2021 A* conf
Towards Enabling Learnware to Handle Unseen Jobs.
AAAI
Yu-Jie Zhang, Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2020 A conf
A Simple Approach for Non-stationary Linear Bandits.
AISTATS
Peng Zhao, Lijun Zhang, Yuan Jiang, Zhi-Hua Zhou
2020 A conf
A Simple Online Algorithm for Competing with Dynamic Comparators.
UAI
Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2020 A* conf
An Unbiased Risk Estimator for Learning with Augmented Classes.
NeurIPS
Yu-Jie Zhang, Peng Zhao, Lanjihong Ma, Zhi-Hua Zhou
2020 A conf
Bandit Convex Optimization in Non-stationary Environments.
AISTATS
Peng Zhao, Guanghui Wang, Lijun Zhang, Zhi-Hua Zhou
2020 A* conf
Dynamic Regret of Convex and Smooth Functions.
NeurIPS
Peng Zhao, Yu-Jie Zhang, Lijun Zhang, Zhi-Hua Zhou
2020 J jnl
Dynamic Regret of Convex and Smooth Functions.
CoRR
Peng Zhao, Yu-Jie Zhang, Lijun Zhang, Zhi-Hua Zhou
2020 J jnl
Exploratory Machine Learning with Unknown Unknowns.
CoRR
Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2020 J jnl
Handling concept drift via model reuse.
Mach. Learn.
Peng Zhao, Le-Wen Cai, Zhi-Hua Zhou
2020 J jnl
Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functions.
CoRR
Peng Zhao, Lijun Zhang
2020 A* conf
Learning with Feature and Distribution Evolvable Streams.
ICML
Zhenyu Zhang, Peng Zhao, Yuan Jiang, Zhi-Hua Zhou
2020 J jnl
Storage Fit Learning with Feature Evolvable Streams.
CoRR
Bo-Jian Hou, Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
2019 J jnl
An Unbiased Risk Estimator for Learning with Augmented Classes.
CoRR
Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
2019 J jnl
Bandit Convex Optimization in Non-stationary Environments.
CoRR
Peng Zhao, Guanghui Wang, Lijun Zhang, Zhi-Hua Zhou
2019 A* conf
Learning from Incomplete and Inaccurate Supervision.
KDD
Zhenyu Zhang, Peng Zhao, Yuan Jiang, Zhi-Hua Zhou
2019 A* conf
Nearest Neighbor Ensembles: An Effective Method for Difficult Problems in Streaming Classification with Emerging New Classes.
ICDM
Xin-Qiang Cai, Peng Zhao, Kai-Ming Ting, Xin Mu, Yuan Jiang
2018 A* conf
Dual Set Multi-Label Learning.
AAAI
Chong Liu, Peng Zhao, Sheng-Jun Huang, Yuan Jiang, Zhi-Hua Zhou
2018 J jnl
Handling Concept Drift via Model Reuse.
CoRR
Peng Zhao, Le-Wen Cai, Zhi-Hua Zhou
2018 A* conf
Improving Deep Forest by Confidence Screening.
ICDM
Ming Pang, Kai-Ming Ting, Peng Zhao, Zhi-Hua Zhou
2018 A* conf
Label Distribution Learning by Optimal Transport.
AAAI
Peng Zhao, Zhi-Hua Zhou
2017 J jnl
Distribution-Free One-Pass Learning.
CoRR
Peng Zhao, Zhi-Hua Zhou
2017 — conf
Multi-View Matrix Completion for Clustering with Side Information.
PAKDD (2)
Peng Zhao, Yuan Jiang, Zhi-Hua Zhou