Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
Comments Accepted by AAAI 2025, Oral
作者
Zhi-Hua Zhou
Machine Learning
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
Comments NeurIPS 2024; v3 substantially improves the presentation and further illustrates the role of $κ$ in function approximation
Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
Comments NeurIPS 2024
Gradient-Variation Online Learning under Generalized Smoothness
Comments NeurIPS 2024
Learnability with Time-Sharing Computational Resource Concerns
Journal ref National Science Review, 11: nwae204, 2024
New Rules for Causal Identification with Background Knowledge
Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution
Comments 25 pages, 7 figures, 1 table. Accepted by Neural Networks
Journal ref Neural Networks, 151:48-60, 2022
Exploratory Machine Learning with Unknown Unknowns
Comments published at Artificial Intelligence, preliminary conference version published at AAAI'21
Journal ref Artificial Intelligence,Volume 327, 2024
Relative Error Bound Analysis for Nuclear Norm Regularized Matrix Completion
Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
Comments NeurIPS 2023
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization
Comments V3 changes: improve the presentation (highlighting the techniques); V2 changes: Updated to improve the presentation (emphasizing the importance of gradient-variation bounds and the contribution of Sword++ algorithm)
Journal ref Journal of Machine Learning Research, 2024
Weakly Supervised AUC Optimization: A Unified Partial AUC Approach
Comments Accepted by IEEE TPAMI
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
Comments AISTATS 2024
Beimingwu: A Learnware Dock System
On the Intrinsic Structures of Spiking Neural Networks
Learnware: Small Models Do Big
Comments Cite as: Zhi-Hua Zhou, Zhi-Hao Tan. Learnware: Small models do big. Science China Information Sciences, 2024, 67(1): 112102.01-112102.12
Journal ref Science China Information Sciences, 2024, 67(1): 112102.01-112102.12
Learning to Coordinate with Anyone
Non-stationary Online Learning with Memory and Non-stochastic Control
Journal ref Journal of Machine Learning Research, 2023
Revisiting Weighted Strategy for Non-stationary Parametric Bandits
Comments AISTATS 2023
LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Values
Journal ref Proceedings of the 21st International Conference on Data Mining (ICDM'21), pages 1511-1516. 2021
Adapting to Online Label Shift with Provable Guarantees
Comments NeurIPS 2022; the first two authors contributed equally
Maximizing Submodular or Monotone Approximately Submodular Functions by Multi-objective Evolutionary Algorithms
Theoretical Exploration of Flexible Transmitter Model
Comments 45 pages, to be published in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
Dynamic Regret of Online Markov Decision Processes
Open-environment Machine Learning
Gas permeation through graphdiyne-based nanoporous membranes
Towards Understanding Theoretical Advantages of Complex-Reaction Networks
Journal ref Neural Networks,151: 80-93. 2022
