理论 · online learning论文趋势 2023–2026

主要结论

• 理论 · online learning论文从 2023 年的 164 篇增长到 2026 年的 190 篇，三年间扩大到约 1.2 倍。
• NeurIPS 是发理论 · online learning论文最多的会议，2023–2026 年共 427 篇，占四个会议总量的 56%。
• 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 12 篇。
• 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的理论 · learning theory是 5.6 倍，理论 · online learning是 1.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
• ICML 2026A Perturbation Approach to Unconstrained Linear Bandits
• ICLR 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
• CVPR 2026An Optimal Transport-driven Approach for Cultivating Latent Space in Online
• NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games
• CVPR 2025InteractionMap: Improving Online Vectorized HDMap Construction with Interaction
• NeurIPS 2024A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
• ICML 2024On Online Experimentation without Device Identifiers
• ICLR 2024Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
• CVPR 2024Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Applied Online Algorithms with Heterogeneous Predictors
• ICLR 2023Hebbian Deep Learning Without Feedback
• CVPR 2023VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos
• NeurIPS 2026A Theory of Adversary-Directed Online Learning
• ICML 2026A Two-Layer Framework for Joint Online Configuration Selection and Admission Control
• ICLR 2026A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
• CVPR 2026Dynamic Momentum Recalibration in Online Gradient Learning

全部理论 · online learning论文

共 169 篇，第 2 / 4 页

51. NeurIPS 2024Fixed Confidence Best Arm Identification in the Bayesian Setting
52. NeurIPS 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
53. NeurIPS 2024Fully Unconstrained Online Learning
54. NeurIPS 2024Generalized Linear Bandits with Limited Adaptivity
55. NeurIPS 2024Global Rewards in Restless Multi-Armed Bandits
56. NeurIPS 2024Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints
57. NeurIPS 2024Gradient-Variation Online Learning under Generalized Smoothness
58. NeurIPS 2024GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
59. NeurIPS 2024Group-wise oracle-efficient algorithms for online multi-group learning
60. NeurIPS 2024HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
61. NeurIPS 2024Honor Among Bandits: No-Regret Learning for Online Fair Division
62. NeurIPS 2024How Does Variance Shape the Regret in Contextual Bandits?
63. NeurIPS 2024Identifying Equivalent Training Dynamics
64. NeurIPS 2024Improved Algorithms for Contextual Dynamic Pricing
65. NeurIPS 2024Improved Analysis for Bandit Learning in Matching Markets
66. NeurIPS 2024Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
67. NeurIPS 2024Improved learning rates in multi-unit uniform price auctions
68. NeurIPS 2024Improved Regret for Bandit Convex Optimization with Delayed Feedback
69. NeurIPS 2024Improved Regret of Linear Ensemble Sampling
70. NeurIPS 2024Information-theoretic Limits of Online Classification with Noisy Labels
71. NeurIPS 2024Label Delay in Online Continual Learning
72. NeurIPS 2024Learning from Snapshots of Discrete and Continuous Data Streams
73. NeurIPS 2024Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
74. NeurIPS 2024Learning to Price Homogeneous Data
75. NeurIPS 2024Learning-Augmented Algorithms with Explicit Predictors
76. NeurIPS 2024Linear Causal Bandits: Unknown Graph and Soft Interventions
77. NeurIPS 2024Local and Adaptive Mirror Descents in Extensive-Form Games
78. NeurIPS 2024Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
79. NeurIPS 2024Localized Adaptive Risk Control
80. NeurIPS 2024Locally Private and Robust Multi-Armed Bandits
81. NeurIPS 2024Lookback Prophet Inequalities
82. NeurIPS 2024Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
83. NeurIPS 2024Maximizing utility in multi-agent environments by anticipating the behavior of other learners
84. NeurIPS 2024MetaCURL: Non-stationary Concave Utility Reinforcement Learning
85. NeurIPS 2024Mixture of Experts Meets Prompt-Based Continual Learning
86. NeurIPS 2024Multi-model Ensemble Conformal Prediction in Dynamic Environments
87. NeurIPS 2024Multiclass Transductive Online Learning
88. NeurIPS 2024Mutli-Armed Bandits with Network Interference
89. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
90. NeurIPS 2024Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
91. NeurIPS 2024Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
92. NeurIPS 2024No-Regret Bandit Exploration based on Soft Tree Ensemble Model
93. NeurIPS 2024No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
94. NeurIPS 2024No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
95. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
96. NeurIPS 2024Off-policy estimation with adaptively collected data: the power of online learning
97. NeurIPS 2024On the Computational Landscape of Replicable Learning
98. NeurIPS 2024On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
99. NeurIPS 2024On the Necessity of Collaboration for Online Model Selection with Decentralized Data
100. NeurIPS 2024On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games

常见问题

2023–2026 年四大会议一共有多少篇理论 · online learning论文？

共 763 篇，按年份分别是 2023 年 164 篇、2024 年 224 篇、2025 年 185 篇、2026 年 190 篇。

NeurIPS 2026 有多少篇理论 · online learning论文？

NeurIPS 2026 有 68 篇理论 · online learning论文，上一届是 89 篇。

ICLR 2026 有多少篇理论 · online learning论文？

ICLR 2026 有 27 篇理论 · online learning论文，上一届是 18 篇。

ICML 2026 有多少篇理论 · online learning论文？

ICML 2026 有 86 篇理论 · online learning论文，上一届是 74 篇。

CVPR 2026 有多少篇理论 · online learning论文？

CVPR 2026 有 9 篇理论 · online learning论文，上一届是 4 篇。

哪个会议的理论 · online learning论文最多？

NeurIPS，2023–2026 年共 427 篇。