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 7 / 8 页

  1. NeurIPS 2025Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
  2. NeurIPS 2025Computable universal online learning
  3. NeurIPS 2025Computational Efficiency under Covariate Shift in Kernel Ridge Regression
  4. NeurIPS 2025Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
  5. NeurIPS 2025Constant Bit-size Transformers Are Turing Complete
  6. NeurIPS 2025Constrained Linear Thompson Sampling
  7. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
  8. NeurIPS 2025Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
  9. NeurIPS 2025Cyclic Counterfactuals under Shift–Scale Interventions
  10. NeurIPS 2025Disentangling Hyperedges through the Lens of Category Theory
  11. NeurIPS 2025Distributional Training Data Attribution: What do Influence Functions Sample?
  12. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
  13. NeurIPS 2025Eluder dimension: localise it!
  14. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
  15. NeurIPS 2025Exact Expressive Power of Transformers with Padding
  16. NeurIPS 2025Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
  17. NeurIPS 2025Fast attention mechanisms: a tale of parallelism
  18. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
  19. NeurIPS 2025How Particle System Theory Enhances Hypergraph Message Passing
  20. NeurIPS 2025Identifiability of Deep Polynomial Neural Networks
  21. NeurIPS 2025Improved Balanced Classification with Theoretically Grounded Loss Functions
  22. NeurIPS 2025Information-Theoretic Discrete Diffusion
  23. NeurIPS 2025Infrequent Exploration in Linear Bandits
  24. NeurIPS 2025Is Grokking a Computational Glass Relaxation?
  25. NeurIPS 2025Knee-Deep in C-RASP: A Transformer Depth Hierarchy
  26. NeurIPS 2025Last Iterate Convergence in Monotone Mean Field Games
  27. NeurIPS 2025Learning from Interval Targets
  28. NeurIPS 2025Learning Interestingness in Automated Mathematical Theory Formation
  29. NeurIPS 2025Learning Linear Attention in Polynomial Time
  30. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
  31. NeurIPS 2025Length Generalization via Auxiliary Tasks
  32. NeurIPS 2025Limitations of Normalization in Attention
  33. NeurIPS 2025Low Precision Streaming PCA
  34. NeurIPS 2025Machine Unlearning under Overparameterization
  35. NeurIPS 2025Marginal-Nonuniform PAC Learnability
  36. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
  37. NeurIPS 2025MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
  38. NeurIPS 2025Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare
  39. NeurIPS 2025Neural Entropy
  40. NeurIPS 2025Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation
  41. NeurIPS 2025Non-Stationary Lipschitz Bandits
  42. NeurIPS 2025Non-Uniform Multiclass Learning with Bandit Feedback
  43. NeurIPS 2025Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
  44. NeurIPS 2025On Agnostic PAC Learning in the Small Error Regime
  45. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
  46. NeurIPS 2025On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
  47. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
  48. NeurIPS 2025On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
  49. NeurIPS 2025On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
  50. NeurIPS 2025On the VC dimension of deep group convolutional 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