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 540 篇，第 4 / 11 页

  1. NeurIPS 2025Information-Theoretic Discrete Diffusion
  2. NeurIPS 2025Infrequent Exploration in Linear Bandits
  3. NeurIPS 2025Is Grokking a Computational Glass Relaxation?
  4. NeurIPS 2025Knee-Deep in C-RASP: A Transformer Depth Hierarchy
  5. NeurIPS 2025Last Iterate Convergence in Monotone Mean Field Games
  6. NeurIPS 2025Learning from Interval Targets
  7. NeurIPS 2025Learning Interestingness in Automated Mathematical Theory Formation
  8. NeurIPS 2025Learning Linear Attention in Polynomial Time
  9. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
  10. NeurIPS 2025Length Generalization via Auxiliary Tasks
  11. NeurIPS 2025Limitations of Normalization in Attention
  12. NeurIPS 2025Low Precision Streaming PCA
  13. NeurIPS 2025Machine Unlearning under Overparameterization
  14. NeurIPS 2025Marginal-Nonuniform PAC Learnability
  15. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
  16. NeurIPS 2025MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
  17. NeurIPS 2025Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare
  18. NeurIPS 2025Neural Entropy
  19. NeurIPS 2025Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation
  20. NeurIPS 2025Non-Stationary Lipschitz Bandits
  21. NeurIPS 2025Non-Uniform Multiclass Learning with Bandit Feedback
  22. NeurIPS 2025Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
  23. NeurIPS 2025On Agnostic PAC Learning in the Small Error Regime
  24. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
  25. NeurIPS 2025On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
  26. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
  27. NeurIPS 2025On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
  28. NeurIPS 2025On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
  29. NeurIPS 2025On the VC dimension of deep group convolutional neural networks
  30. NeurIPS 2025On Transferring Transferability: Towards a Theory for Size Generalization
  31. NeurIPS 2025On Universality Classes of Equivariant Networks
  32. NeurIPS 2025Online Learning in the Repeated Mediated Newsvendor Problem
  33. NeurIPS 2025Online Learning of Neural Networks
  34. NeurIPS 2025Optimism Without Regularization: Constant Regret in Zero-Sum Games
  35. NeurIPS 2025Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
  36. NeurIPS 2025Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
  37. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
  38. NeurIPS 2025Product Distribution Learning with Imperfect Advice
  39. NeurIPS 2025Regularized least squares learning with heavy-tailed noise is minimax optimal
  40. NeurIPS 2025Replicable Distribution Testing
  41. NeurIPS 2025Revisiting Agnostic Boosting
  42. NeurIPS 2025Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
  43. NeurIPS 2025Robust learning of halfspaces under log-concave marginals
  44. NeurIPS 2025Robustly Learning Monotone Single-Index Models
  45. NeurIPS 2025Safely Learning Controlled Stochastic Dynamics
  46. NeurIPS 2025Sample-Conditional Coverage in Split-Conformal Prediction
  47. NeurIPS 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
  48. NeurIPS 2025Sharp Matrix Empirical Bernstein Inequalities
  49. NeurIPS 2025Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
  50. NeurIPS 2025Smoothed Agnostic Learning of Halfspaces over the Hypercube

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