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 16 / 27 页

  1. ICML 2025Towards a Formal Theory of Representational Compositionality
  2. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  3. ICML 2025Training Dynamics of In-Context Learning in Linear Attention
  4. ICML 2025Transfer Q-Learning with Composite MDP Structures
  5. ICML 2025Tree-Sliced Wasserstein Distance: A Geometric Perspective
  6. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
  7. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
  8. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
  9. ICML 2025Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data
  10. ICML 2025Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means
  11. ICML 2025Universal Length Generalization with Turing Programs
  12. ICML 2025Weak-to-Strong Generalization Even in Random Feature Networks, Provably
  13. ICML 2025Weight matrices compression based on PDB model in deep neural networks
  14. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
  15. ICML 2025When do neural networks learn world models?
  16. NeurIPS 2025A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
  17. NeurIPS 2025A Geometric Analysis of PCA
  18. NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
  19. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
  20. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
  21. NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
  22. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
  23. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
  24. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
  25. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
  26. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
  27. NeurIPS 2025Benign Overfitting in Single-Head Attention
  28. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
  29. NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
  30. NeurIPS 2025Block Coordinate Descent for Neural Networks Provably Finds Global Minima
  31. NeurIPS 2025Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
  32. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
  33. NeurIPS 2025Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
  34. NeurIPS 2025Computable universal online learning
  35. NeurIPS 2025Computational Efficiency under Covariate Shift in Kernel Ridge Regression
  36. NeurIPS 2025Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
  37. NeurIPS 2025Constant Bit-size Transformers Are Turing Complete
  38. NeurIPS 2025Constrained Linear Thompson Sampling
  39. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
  40. NeurIPS 2025Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
  41. NeurIPS 2025Cyclic Counterfactuals under Shift–Scale Interventions
  42. NeurIPS 2025Disentangling Hyperedges through the Lens of Category Theory
  43. NeurIPS 2025Distributional Training Data Attribution: What do Influence Functions Sample?
  44. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
  45. NeurIPS 2025Eluder dimension: localise it!
  46. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
  47. NeurIPS 2025Exact Expressive Power of Transformers with Padding
  48. NeurIPS 2025Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
  49. NeurIPS 2025Fast attention mechanisms: a tale of parallelism
  50. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits

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