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 389 篇，第 6 / 8 页

  1. ICML 2025Representative Language Generation
  2. ICML 2025Rethinking Benign Overfitting in Two-Layer Neural Networks
  3. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
  4. ICML 2025Revisiting the Predictability of Performative, Social Events
  5. ICML 2025Sample-Optimal Agnostic Boosting with Unlabeled Data
  6. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
  7. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
  8. ICML 2025Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness
  9. ICML 2025Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
  10. ICML 2025System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
  11. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
  12. ICML 2025The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
  13. ICML 2025The impact of uncertainty on regularized learning in games
  14. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
  15. ICML 2025The Role of Randomness in Stability
  16. ICML 2025Theoretical Limitations of Ensembles in the Age of Overparameterization
  17. ICML 2025Tight and Fast Bounds for Multi-Label Learning
  18. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  19. ICML 2025Towards a Formal Theory of Representational Compositionality
  20. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  21. ICML 2025Training Dynamics of In-Context Learning in Linear Attention
  22. ICML 2025Transfer Q-Learning with Composite MDP Structures
  23. ICML 2025Tree-Sliced Wasserstein Distance: A Geometric Perspective
  24. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
  25. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
  26. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
  27. ICML 2025Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data
  28. ICML 2025Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means
  29. ICML 2025Universal Length Generalization with Turing Programs
  30. ICML 2025Weak-to-Strong Generalization Even in Random Feature Networks, Provably
  31. ICML 2025Weight matrices compression based on PDB model in deep neural networks
  32. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
  33. ICML 2025When do neural networks learn world models?
  34. NeurIPS 2025A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
  35. NeurIPS 2025A Geometric Analysis of PCA
  36. NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
  37. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
  38. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
  39. NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
  40. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
  41. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
  42. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
  43. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
  44. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
  45. NeurIPS 2025Benign Overfitting in Single-Head Attention
  46. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
  47. NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
  48. NeurIPS 2025Block Coordinate Descent for Neural Networks Provably Finds Global Minima
  49. NeurIPS 2025Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
  50. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective

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