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 1,350 篇，第 19 / 27 页

  1. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms
  2. ICLR 2024Generalization error of spectral algorithms
  3. ICLR 2024Generalization of Scaled Deep ResNets in the Mean-Field Regime
  4. ICLR 2024Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
  5. ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
  6. ICLR 2024High-dimensional SGD aligns with emerging outlier eigenspaces
  7. ICLR 2024Horizon-Free Regret for Linear Markov Decision Processes
  8. ICLR 2024How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
  9. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
  10. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
  11. ICLR 2024Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
  12. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
  13. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
  14. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
  15. ICLR 2024Incentivized Truthful Communication for Federated Bandits
  16. ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
  17. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
  18. ICLR 2024Koopman-based generalization bound: New aspect for full-rank weights
  19. ICLR 2024Learning Conditional Invariances through Non-Commutativity
  20. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
  21. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
  22. ICLR 2024Learning Nash Equilibria in Rank-1 Games
  23. ICLR 2024Learning Thresholds with Latent Values and Censored Feedback
  24. ICLR 2024Learning to Reject Meets Long-tail Learning
  25. ICLR 2024Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
  26. ICLR 2024lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
  27. ICLR 2024Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
  28. ICLR 2024Memorization Capacity of Multi-Head Attention in Transformers
  29. ICLR 2024Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
  30. ICLR 2024Minimum width for universal approximation using ReLU networks on compact domain
  31. ICLR 2024More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
  32. ICLR 2024Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
  33. ICLR 2024Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
  34. ICLR 2024Noisy Interpolation Learning with Shallow Univariate ReLU Networks
  35. ICLR 2024On Representation Complexity of Model-based and Model-free Reinforcement Learning
  36. ICLR 2024On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
  37. ICLR 2024On the hardness of learning under symmetries
  38. ICLR 2024On the Limitations of Temperature Scaling for Distributions with Overlaps
  39. ICLR 2024On the Provable Advantage of Unsupervised Pretraining
  40. ICLR 2024One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
  41. ICLR 2024Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
  42. ICLR 2024OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
  43. ICLR 2024Optimal Sample Complexity of Contrastive Learning
  44. ICLR 2024Oracle Efficient Algorithms for Groupwise Regret
  45. ICLR 2024Out-Of-Domain Unlabeled Data Improves Generalization
  46. ICLR 2024Plugin estimators for selective classification with out-of-distribution detection
  47. ICLR 2024Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
  48. ICLR 2024Provable Offline Preference-Based Reinforcement Learning
  49. ICLR 2024Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
  50. ICLR 2024Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse 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