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 427 篇，第 2 / 9 页

  1. NeurIPS 2026OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
  2. NeurIPS 2026Personalized and Collaborative Online LQR via Thompson Sampling
  3. NeurIPS 2026Posterior Sampling-based Online Learning for Episodic POMDPs
  4. NeurIPS 2026Propagation of Chaos in Contextual Flow Maps
  5. NeurIPS 2026Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
  6. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
  7. NeurIPS 2026Replicable Constrained Bandits
  8. NeurIPS 2026Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
  9. NeurIPS 2026RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
  10. NeurIPS 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
  11. NeurIPS 2026Speed Predictions for Online Energy-Efficient Scheduling
  12. NeurIPS 2026Strongly Adaptive Online Learning with Time-Varying Movement Cost
  13. NeurIPS 2026Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
  14. NeurIPS 2026The Minimax Rate of Online Isotonic Regression on Product Orders
  15. NeurIPS 2026The Power of a Random Sample in Online Algorithms
  16. NeurIPS 2026Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
  17. NeurIPS 2026Toward Online Robust Zero-Sum Markov Games with Function Approximation
  18. NeurIPS 2026When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
  19. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
  20. NeurIPS 2025Agnostic Continuous-Time Online Learning
  21. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
  22. NeurIPS 2025Asymptotic theory of SGD with a general learning-rate
  23. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
  24. NeurIPS 2025Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
  25. NeurIPS 2025Computable universal online learning
  26. NeurIPS 2025Conformal Online Learning of Deep Koopman Linear Embeddings
  27. NeurIPS 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
  28. NeurIPS 2025Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
  29. NeurIPS 2025Contextual Online Pricing with (Biased) Offline Data
  30. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
  31. NeurIPS 2025Efficient Last-Iterate Convergence in Solving Extensive-Form Games
  32. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
  33. NeurIPS 2025Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
  34. NeurIPS 2025Explaining the Law of Supply and Demand via Online Learning
  35. NeurIPS 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
  36. NeurIPS 2025Exploring the Noise Robustness of Online Conformal Prediction
  37. NeurIPS 2025Fair Matroid Selection
  38. NeurIPS 2025Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
  39. NeurIPS 2025From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
  40. NeurIPS 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
  41. NeurIPS 2025Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
  42. NeurIPS 2025Gradient-Guided Epsilon Constraint Method for Online Continual Learning
  43. NeurIPS 2025High-Dimensional Calibration from Swap Regret
  44. NeurIPS 2025HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location
  45. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
  46. NeurIPS 2025Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
  47. NeurIPS 2025Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints
  48. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
  49. NeurIPS 2025Kernel conditional tests from learning-theoretic bounds
  50. NeurIPS 2025Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

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