理论 · online learning论文趋势 2023–2026

学习理论及相关：online_learning

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 763 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

理论 · online learning论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202310117397164
202416913348224
20258918744185
20266827869190

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

全部理论 · online learning论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 233 篇，第 3 / 5 页

  1. ICML 2025Contextual Linear Bandits with Delay as Payoff
  2. ICML 2025Contextual Online Decision Making with Infinite-Dimensional Functional Regression
  3. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
  4. ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
  5. ICML 2025Exploiting Curvature in Online Convex Optimization with Delayed Feedback
  6. ICML 2025Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
  7. ICML 2025Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
  8. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
  9. ICML 2025Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
  10. ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
  11. ICML 2025Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
  12. ICML 2025High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
  13. ICML 2025High-Dimensional Prediction for Sequential Decision Making
  14. ICML 2025Improved Online Confidence Bounds for Multinomial Logistic Bandits
  15. ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
  16. ICML 2025Learning Adversarial MDPs with Stochastic Hard Constraints
  17. ICML 2025Learning With Multi-Group Guarantees For Clusterable Subpopulations
  18. ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
  19. ICML 2025Leveraging Offline Data in Linear Latent Contextual Bandits
  20. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
  21. ICML 2025Linear Bandits with Partially Observable Features
  22. ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning
  23. ICML 2025Maintaining Proportional Committees with Dynamic Candidate Sets
  24. ICML 2025Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
  25. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification
  26. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
  27. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
  28. ICML 2025Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
  29. ICML 2025Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
  30. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
  31. ICML 2025On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
  32. ICML 2025Online Clustering of Dueling Bandits
  33. ICML 2025Online Conformal Prediction via Online Optimization
  34. ICML 2025Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
  35. ICML 2025Online Episodic Convex Reinforcement Learning
  36. ICML 2025Online Laplacian-Based Representation Learning in Reinforcement Learning
  37. ICML 2025Online Learning in Risk Sensitive constrained MDP
  38. ICML 2025Online Learning in the Random-Order Model
  39. ICML 2025Online Learning with Unknown Constraints
  40. ICML 2025Online Linear Classification with Massart Noise
  41. ICML 2025Online Pre-Training for Offline-to-Online Reinforcement Learning
  42. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
  43. ICML 2025Optimal Algorithm for Max-Min Fair Bandit
  44. ICML 2025Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
  45. ICML 2025Partially Observable Reinforcement Learning with Memory Traces
  46. ICML 2025Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
  47. ICML 2025Revisiting Differentially Private Algorithms for Decentralized Online Learning
  48. ICML 2025Revisiting the Predictability of Performative, Social Events
  49. ICML 2025Reward-free World Models for Online Imitation Learning
  50. ICML 2025Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查理论 · online learning在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "theory-online-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「理论与统计」下的其他主题