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 9 / 27 页

  1. NeurIPS 2026Estimating Implicit Regularization in Deep Learning
  2. NeurIPS 2026Estimating the expected output of wide random MLPs more efficiently than sampling
  3. NeurIPS 2026Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
  4. NeurIPS 2026Fast Learning Rates for Physics-Informed Kernel Methods
  5. NeurIPS 2026Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
  6. NeurIPS 2026First-Order Regret for Online Convex Optimization with Memory and Online Nonstochastic Control
  7. NeurIPS 2026Fixed Universal Transformers
  8. NeurIPS 2026Foundations of Categorical Equivariant Deep Learning
  9. NeurIPS 2026From POMDP Theory to Deep RL with Particle Filters
  10. NeurIPS 2026Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems
  11. NeurIPS 2026Generalization Bounds for Neural Networks with Sparse Connectivity
  12. NeurIPS 2026Generating in the Limit with Infinitely Many Hallucinations
  13. NeurIPS 2026Global Convergence in Deep Networks via the Second Law of Thermodynamics
  14. NeurIPS 2026Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
  15. NeurIPS 2026High dimensional theory of two-phase optimizers
  16. NeurIPS 2026High-arity Sample Compression
  17. NeurIPS 2026How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
  18. NeurIPS 2026Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
  19. NeurIPS 2026Improved Algorithms for Online Classification with Surrogate Losses
  20. NeurIPS 2026Inference and Uncertainty Quantification for Streaming $r$-PCA
  21. NeurIPS 2026Inference Time Nash Alignment
  22. NeurIPS 2026Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
  23. NeurIPS 2026InfoFlow: A Framework for Multi-Layer Transformer Analysis
  24. NeurIPS 2026Information Loss and Disparate Effects in Network Embeddings
  25. NeurIPS 2026Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances
  26. NeurIPS 2026Learning Chance-Constrained MDPs with Bellman Distributional Certificates
  27. NeurIPS 2026Learning Lotteries with Minimal Violations from Membership Queries
  28. NeurIPS 2026Learning to Audit ML Models with Theory of Mind
  29. NeurIPS 2026Less Structure is More: Minimal Representations for Supervised Learning
  30. NeurIPS 2026Linear Contextual Bandits with Quasi-Optimism
  31. NeurIPS 2026Linear Ensemble Sampling with Fewer Ensembles
  32. NeurIPS 2026Looped Transformers with Layer Normalization Provably Learn the Power Method
  33. NeurIPS 2026Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
  34. NeurIPS 2026Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
  35. NeurIPS 2026MinMax Recurrent Neural Cascades
  36. NeurIPS 2026Model Collapse is a Singular Complexity Trajectory
  37. NeurIPS 2026Multi-Armed Bandits With Best-Action Queries
  38. NeurIPS 2026Multiple Descent of Generalization Curve for Optimally Regularized Ridge Regression
  39. NeurIPS 2026Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
  40. NeurIPS 2026Network Intervention by Polling Strategic Agents
  41. NeurIPS 2026Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers
  42. NeurIPS 2026On Concentration Inequalities for Sampling without Replacement
  43. NeurIPS 2026On the Complexity of Preference-Based Bandits
  44. NeurIPS 2026One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought
  45. NeurIPS 2026Online Directional Regression for Streaming Sufficient Dimension Reduction
  46. NeurIPS 2026Online Resource Allocation With General Constraints
  47. NeurIPS 2026Online Set Learning from Precision and Recall Feedback
  48. NeurIPS 2026Optimal Dimension-Free Sampling for Regularized Classification
  49. NeurIPS 2026PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
  50. NeurIPS 2026Parameter symmetries determine representational geometry in overparameterized nonlinear 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