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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 101 | 17 | 39 | 7 | 164 |
| 2024 | 169 | 13 | 34 | 8 | 224 |
| 2025 | 89 | 18 | 74 | 4 | 185 |
| 2026 | 68 | 27 | 86 | 9 | 190 |
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 763 篇，第 5 / 16 页
- ICLR 2025Feature-Based Online Bilateral Trade
- ICLR 2025Hessian-Free Online Certified Unlearning
- ICLR 2025Longhorn: State Space Models are Amortized Online Learners
- ICLR 2025Minimalistic Predictions for Online Class Constraint Scheduling
- ICLR 2025On Bits and Bandits: Quantifying the Regret-Information Trade-off
- ICLR 2025Online Clustering with Nearly Optimal Consistency
- ICLR 2025ONLINE EPSILON NET & PIERCING SET FOR GEOMETRIC CONCEPTS
- ICLR 2025Online Reinforcement Learning in Non-Stationary Context-Driven Environments
- ICLR 2025Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
- ICLR 2025Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
- ICLR 2025Satisficing Regret Minimization in Bandits
- ICLR 2025Simplifying Deep Temporal Difference Learning
- ICML 2025A Classification View on Meta Learning Bandits
- ICML 2025A Online Statistical Framework for Out-of-Distribution Detection
- ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
- ICML 2025A Trichotomy for List Transductive Online Learning
- ICML 2025AKORN: Adaptive Knots generated Online for RegressioN splines
- ICML 2025Algorithms with Calibrated Machine Learning Predictions
- ICML 2025Avoiding Catastrophe in Online Learning by Asking for Help
- ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
- ICML 2025Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
- ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
- ICML 2025Competitively Consistent Clustering
- ICML 2025Constrained Online Convex Optimization with Polyak Feasibility Steps
- ICML 2025Constrained Pareto Set Identification with Bandit Feedback
- ICML 2025Contextual Bandits for Unbounded Context Distributions
- ICML 2025Contextual Linear Bandits with Delay as Payoff
- ICML 2025Contextual Online Decision Making with Infinite-Dimensional Functional Regression
- ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
- ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
- ICML 2025Exploiting Curvature in Online Convex Optimization with Delayed Feedback
- ICML 2025Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
- ICML 2025Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
- ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
- ICML 2025Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
- ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
- ICML 2025Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
- ICML 2025High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
- ICML 2025High-Dimensional Prediction for Sequential Decision Making
- ICML 2025Improved Online Confidence Bounds for Multinomial Logistic Bandits
- ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
- ICML 2025Learning Adversarial MDPs with Stochastic Hard Constraints
- ICML 2025Learning With Multi-Group Guarantees For Clusterable Subpopulations
- ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
- ICML 2025Leveraging Offline Data in Linear Latent Contextual Bandits
- ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
- ICML 2025Linear Bandits with Partially Observable Features
- ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning
- ICML 2025Maintaining Proportional Committees with Dynamic Candidate Sets
- ICML 2025Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
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"}
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。