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 26 / 27 页

  1. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
  2. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
  3. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
  4. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation
  5. NeurIPS 2024Understanding the Role of Equivariance in Self-supervised Learning
  6. NeurIPS 2024Universal Rates for Active Learning
  7. NeurIPS 2024Universal Rates of Empirical Risk Minimization
  8. NeurIPS 2024Universality in Transfer Learning for Linear Models
  9. NeurIPS 2024Unravelling in Collaborative Learning
  10. NeurIPS 2024Unrolled denoising networks provably learn to perform optimal Bayesian inference
  11. NeurIPS 2024Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
  12. NeurIPS 2024Variance estimation in compound decision theory under boundedness
  13. NeurIPS 2024Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
  14. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
  15. ICLR 2023A Theory of Dynamic Benchmarks
  16. ICLR 2023Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation
  17. ICLR 2023Bispectral Neural Networks
  18. ICLR 2023Computational Language Acquisition with Theory of Mind
  19. ICLR 2023D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
  20. ICLR 2023Disentanglement with Biological Constraints: A Theory of Functional Cell Types
  21. ICLR 2023Humanly Certifying Superhuman Classifiers
  22. ICLR 2023Learning in temporally structured environments
  23. ICLR 2023Learning Probabilistic Topological Representations Using Discrete Morse Theory
  24. ICLR 2023Learning ReLU networks to high uniform accuracy is intractable
  25. ICLR 2023Long-Tailed Learning Requires Feature Learning
  26. ICLR 2023Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
  27. ICLR 2023Pitfalls of Gaussians as a noise distribution in NCE
  28. ICLR 2023Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
  29. ICLR 2023Provable Memorization Capacity of Transformers
  30. ICLR 2023Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process
  31. ICLR 2023Spacetime Representation Learning
  32. ICLR 2023Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms
  33. ICLR 2023Strong inductive biases provably prevent harmless interpolation
  34. ICLR 2023Systematic Rectification of Language Models via Dead-end Analysis
  35. ICLR 2023The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
  36. ICLR 2023Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs
  37. ICLR 2023Transformers Learn Shortcuts to Automata
  38. ICLR 2023Why adversarial training can hurt robust accuracy
  39. ICML 2023Certifying Ensembles: A General Certification Theory with S-Lipschitzness
  40. ICML 2023Fast Federated Machine Unlearning with Nonlinear Functional Theory
  41. ICML 2023Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
  42. ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
  43. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
  44. NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
  45. NeurIPS 2023A Measure-Theoretic Axiomatisation of Causality
  46. NeurIPS 2023A Theory of Multimodal Learning
  47. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
  48. NeurIPS 2023Accelerating Value Iteration with Anchoring
  49. NeurIPS 2023Agnostic Multi-Group Active Learning
  50. NeurIPS 2023Alternation makes the adversary weaker in two-player games

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