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 5 / 8 页

  1. ICML 2025Hypothesis Testing for Generalized Thurstone Models
  2. ICML 2025Identifying Metric Structures of Deep Latent Variable Models
  3. ICML 2025Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
  4. ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
  5. ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
  6. ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
  7. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
  8. ICML 2025Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
  9. ICML 2025Learning Parametric Distributions from Samples and Preferences
  10. ICML 2025Learning to Steer Learners in Games
  11. ICML 2025Learning Utilities from Demonstrations in Markov Decision Processes
  12. ICML 2025Learning with Exact Invariances in Polynomial Time
  13. ICML 2025Learning-Augmented Hierarchical Clustering
  14. ICML 2025Limitations of measure-first protocols in quantum machine learning
  15. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
  16. ICML 2025Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
  17. ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
  18. ICML 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
  19. ICML 2025Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
  20. ICML 2025Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
  21. ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
  22. ICML 2025Models of Heavy-Tailed Mechanistic Universality
  23. ICML 2025Modular Duality in Deep Learning
  24. ICML 2025Nearly Optimal Sample Complexity for Learning with Label Proportions
  25. ICML 2025No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
  26. ICML 2025Non-Asymptotic Length Generalization
  27. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
  28. ICML 2025Nonlinear transformers can perform inference-time feature learning
  29. ICML 2025On Learning Parallel Pancakes with Mostly Uniform Weights
  30. ICML 2025On the Convergence of Continuous Single-timescale Actor-critic
  31. ICML 2025On the Emergence of Position Bias in Transformers
  32. ICML 2025On the Generalization Ability of Next-Token-Prediction Pretraining
  33. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
  34. ICML 2025On the Role of Label Noise in the Feature Learning Process
  35. ICML 2025On the Similarities of Embeddings in Contrastive Learning
  36. ICML 2025On the Statistical Mechanisms of Distributional Compositional Generalization
  37. ICML 2025On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
  38. ICML 2025PAC Learning with Improvements
  39. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
  40. ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
  41. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
  42. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
  43. ICML 2025Probably Approximately Global Robustness Certification
  44. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
  45. ICML 2025Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
  46. ICML 2025Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
  47. ICML 2025Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
  48. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
  49. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
  50. ICML 2025Representation Preserving Multiclass Agnostic to Realizable Reduction

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