理论 · learning theory论文趋势 2023–2026

学习理论及相关：learning_theory

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,350 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 · learning theory论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202357245086
2024265106211393
20251061471324389
20261122001700482

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 · learning theory论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 328 篇，第 6 / 7 页

  1. ICML 2025On the Generalization Ability of Next-Token-Prediction Pretraining
  2. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
  3. ICML 2025On the Role of Label Noise in the Feature Learning Process
  4. ICML 2025On the Similarities of Embeddings in Contrastive Learning
  5. ICML 2025On the Statistical Mechanisms of Distributional Compositional Generalization
  6. ICML 2025On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
  7. ICML 2025PAC Learning with Improvements
  8. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
  9. ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
  10. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
  11. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
  12. ICML 2025Probably Approximately Global Robustness Certification
  13. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
  14. ICML 2025Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
  15. ICML 2025Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
  16. ICML 2025Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
  17. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
  18. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
  19. ICML 2025Representation Preserving Multiclass Agnostic to Realizable Reduction
  20. ICML 2025Representative Language Generation
  21. ICML 2025Rethinking Benign Overfitting in Two-Layer Neural Networks
  22. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
  23. ICML 2025Revisiting the Predictability of Performative, Social Events
  24. ICML 2025Sample-Optimal Agnostic Boosting with Unlabeled Data
  25. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
  26. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
  27. ICML 2025Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness
  28. ICML 2025Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
  29. ICML 2025System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
  30. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
  31. ICML 2025The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
  32. ICML 2025The impact of uncertainty on regularized learning in games
  33. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
  34. ICML 2025The Role of Randomness in Stability
  35. ICML 2025Theoretical Limitations of Ensembles in the Age of Overparameterization
  36. ICML 2025Tight and Fast Bounds for Multi-Label Learning
  37. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  38. ICML 2025Towards a Formal Theory of Representational Compositionality
  39. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  40. ICML 2025Training Dynamics of In-Context Learning in Linear Attention
  41. ICML 2025Transfer Q-Learning with Composite MDP Structures
  42. ICML 2025Tree-Sliced Wasserstein Distance: A Geometric Perspective
  43. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
  44. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
  45. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
  46. ICML 2025Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data
  47. ICML 2025Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means
  48. ICML 2025Universal Length Generalization with Turing Programs
  49. ICML 2025Weak-to-Strong Generalization Even in Random Feature Networks, Provably
  50. ICML 2025Weight matrices compression based on PDB model in deep neural networks

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 · learning theory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-learning-theory"}

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 · learning theory论文？
共 1,350 篇，按年份分别是 2023 年 86 篇、2024 年 393 篇、2025 年 389 篇、2026 年 482 篇。
NeurIPS 2026 有多少篇理论 · learning theory论文？
NeurIPS 2026 有 112 篇理论 · learning theory论文，上一届是 106 篇。
ICLR 2026 有多少篇理论 · learning theory论文？
ICLR 2026 有 200 篇理论 · learning theory论文，上一届是 147 篇。
ICML 2026 有多少篇理论 · learning theory论文？
ICML 2026 有 170 篇理论 · learning theory论文，上一届是 132 篇。
CVPR 2025 有多少篇理论 · learning theory论文？
CVPR 2025 有 4 篇理论 · learning theory论文，上一届是 1 篇。
哪个会议的理论 · learning theory论文最多？
NeurIPS，2023–2026 年共 540 篇。

「理论与统计」下的其他主题