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 8 / 11 页

  1. NeurIPS 2024Linear Regression using Heterogeneous Data Batches
  2. NeurIPS 2024Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
  3. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
  4. NeurIPS 2024Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
  5. NeurIPS 2024Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
  6. NeurIPS 2024Metric Transforms and Low Rank Representations of Kernels for Fast Attention
  7. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
  8. NeurIPS 2024Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
  9. NeurIPS 2024Model Collapse Demystified: The Case of Regression
  10. NeurIPS 2024Multi-Label Learning with Stronger Consistency Guarantees
  11. NeurIPS 2024Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
  12. NeurIPS 2024Nature-Inspired Local Propagation
  13. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
  14. NeurIPS 2024Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
  15. NeurIPS 2024Neural Collapse To Multiple Centers For Imbalanced Data
  16. NeurIPS 2024Neural Conditional Probability for Uncertainty Quantification
  17. NeurIPS 2024Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
  18. NeurIPS 2024NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
  19. NeurIPS 2024Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
  20. NeurIPS 2024Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
  21. NeurIPS 2024Non-asymptotic Convergence of Training Transformers for Next-token Prediction
  22. NeurIPS 2024Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
  23. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
  24. NeurIPS 2024On $f$-Divergence Principled Domain Adaptation: An Improved Framework
  25. NeurIPS 2024On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
  26. NeurIPS 2024On the Ability of Developers' Training Data Preservation of Learnware
  27. NeurIPS 2024On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
  28. NeurIPS 2024On the Computational Landscape of Replicable Learning
  29. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
  30. NeurIPS 2024On the Efficiency of ERM in Feature Learning
  31. NeurIPS 2024On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
  32. NeurIPS 2024On the Limitations of Fractal Dimension as a Measure of Generalization
  33. NeurIPS 2024On the Power of Decision Trees in Auto-Regressive Language Modeling
  34. NeurIPS 2024On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
  35. NeurIPS 2024On the Role of Attention Masks and LayerNorm in Transformers
  36. NeurIPS 2024On the Saturation Effects of Spectral Algorithms in Large Dimensions
  37. NeurIPS 2024On the Sparsity of the Strong Lottery Ticket Hypothesis
  38. NeurIPS 2024On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
  39. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
  40. NeurIPS 2024Online Consistency of the Nearest Neighbor Rule
  41. NeurIPS 2024Online Weighted Paging with Unknown Weights
  42. NeurIPS 2024Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
  43. NeurIPS 2024Optimal Algorithms for Augmented Testing of Discrete Distributions
  44. NeurIPS 2024Optimal Algorithms for Learning Partitions with Faulty Oracles
  45. NeurIPS 2024Optimal deep learning of holomorphic operators between Banach spaces
  46. NeurIPS 2024Optimal Hypothesis Selection in (Almost) Linear Time
  47. NeurIPS 2024Optimal Parallelization of Boosting
  48. NeurIPS 2024Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
  49. NeurIPS 2024Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
  50. NeurIPS 2024Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality

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