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 224 篇，第 1 / 5 页

1. CVPR 2024Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning
2. CVPR 2024Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning
3. CVPR 2024DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
4. CVPR 2024Flow-Guided Online Stereo Rectification for Wide Baseline Stereo
5. CVPR 2024Improving Plasticity in Online Continual Learning via Collaborative Learning
6. CVPR 2024Learning Equi-angular Representations for Online Continual Learning
7. CVPR 2024MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction
8. CVPR 2024PREGO: Online Mistake Detection in PRocedural EGOcentric Videos
9. ICLR 2024Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
10. ICLR 2024Bandits with Replenishable Knapsacks: the Best of both Worlds
11. ICLR 2024Contextual Bandits with Online Neural Regression
12. ICLR 2024Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
13. ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
14. ICLR 2024Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
15. ICLR 2024Kalman Filter for Online Classification of Non-Stationary Data
16. ICLR 2024Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
17. ICLR 2024Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
18. ICLR 2024Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
19. ICLR 2024Online Stabilization of Spiking Neural Networks
20. ICLR 2024Oracle Efficient Algorithms for Groupwise Regret
21. ICLR 2024RLIF: Interactive Imitation Learning as Reinforcement Learning
22. ICML 2024Adaptively Learning to Select-Rank in Online Platforms
23. ICML 2024ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories
24. ICML 2024BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition
25. ICML 2024Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
26. ICML 2024Convergence of Online Learning Algorithm for a Mixture of Multiple Linear Regressions
27. ICML 2024Discounted Adaptive Online Learning: Towards Better Regularization
28. ICML 2024Efficient Online Set-valued Classification with Bandit Feedback
29. ICML 2024Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
30. ICML 2024Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
31. ICML 2024MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
32. ICML 2024Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning
33. ICML 2024NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks
34. ICML 2024Non-parametric Online Change Point Detection on Riemannian Manifolds
35. ICML 2024OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
36. ICML 2024On Online Experimentation without Device Identifiers
37. ICML 2024Online Adaptive Anomaly Thresholding with Confidence Sequences
38. ICML 2024Online Algorithms with Uncertainty-Quantified Predictions
39. ICML 2024Online bipartite matching with imperfect advice
40. ICML 2024Online Cascade Learning for Efficient Inference over Streams
41. ICML 2024Online conformal prediction with decaying step sizes
42. ICML 2024Online Isolation Forest
43. ICML 2024Online Learning in Betting Markets: Profit versus Prediction
44. ICML 2024Online Learning with Bounded Recall
45. ICML 2024Online Linear Regression in Dynamic Environments via Discounting
46. ICML 2024Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning
47. ICML 2024Online Matrix Completion: A Collaborative Approach with Hott Items
48. ICML 2024Online Resource Allocation with Non-Stationary Customers
49. ICML 2024Online Speculative Decoding
50. ICML 2024Online Variational Sequential Monte Carlo

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。