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 86 篇，第 1 / 2 页

  1. ICLR 2023A Theory of Dynamic Benchmarks
  2. ICLR 2023Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation
  3. ICLR 2023Bispectral Neural Networks
  4. ICLR 2023Computational Language Acquisition with Theory of Mind
  5. ICLR 2023D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
  6. ICLR 2023Disentanglement with Biological Constraints: A Theory of Functional Cell Types
  7. ICLR 2023Humanly Certifying Superhuman Classifiers
  8. ICLR 2023Learning in temporally structured environments
  9. ICLR 2023Learning Probabilistic Topological Representations Using Discrete Morse Theory
  10. ICLR 2023Learning ReLU networks to high uniform accuracy is intractable
  11. ICLR 2023Long-Tailed Learning Requires Feature Learning
  12. ICLR 2023Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
  13. ICLR 2023Pitfalls of Gaussians as a noise distribution in NCE
  14. ICLR 2023Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
  15. ICLR 2023Provable Memorization Capacity of Transformers
  16. ICLR 2023Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process
  17. ICLR 2023Spacetime Representation Learning
  18. ICLR 2023Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms
  19. ICLR 2023Strong inductive biases provably prevent harmless interpolation
  20. ICLR 2023Systematic Rectification of Language Models via Dead-end Analysis
  21. ICLR 2023The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
  22. ICLR 2023Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs
  23. ICLR 2023Transformers Learn Shortcuts to Automata
  24. ICLR 2023Why adversarial training can hurt robust accuracy
  25. ICML 2023Certifying Ensembles: A General Certification Theory with S-Lipschitzness
  26. ICML 2023Fast Federated Machine Unlearning with Nonlinear Functional Theory
  27. ICML 2023Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
  28. ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
  29. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
  30. NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
  31. NeurIPS 2023A Measure-Theoretic Axiomatisation of Causality
  32. NeurIPS 2023A Theory of Multimodal Learning
  33. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
  34. NeurIPS 2023Accelerating Value Iteration with Anchoring
  35. NeurIPS 2023Agnostic Multi-Group Active Learning
  36. NeurIPS 2023Alternation makes the adversary weaker in two-player games
  37. NeurIPS 2023Bandit Social Learning under Myopic Behavior
  38. NeurIPS 2023Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
  39. NeurIPS 2023Bridging RL Theory and Practice with the Effective Horizon
  40. NeurIPS 2023Characterization of Overfitting in Robust Multiclass Classification
  41. NeurIPS 2023Common Ground in Cooperative Communication
  42. NeurIPS 2023Delegated Classification
  43. NeurIPS 2023Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback
  44. NeurIPS 2023Equivariant Neural Operator Learning with Graphon Convolution
  45. NeurIPS 2023Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
  46. NeurIPS 2023Faster Relative Entropy Coding with Greedy Rejection Coding
  47. NeurIPS 2023Feature Selection in the Contrastive Analysis Setting
  48. NeurIPS 2023Finding Safe Zones of Markov Decision Processes Policies
  49. NeurIPS 2023Generalized Belief Transport
  50. NeurIPS 2023Information Theoretic Lower Bounds for Information Theoretic Upper Bounds

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