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 7 / 27 页

  1. ICML 2026On the Accuracy of Newton Step and Influence Function Data Attributions
  2. ICML 2026On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
  3. ICML 2026On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
  4. ICML 2026On the Power of Source Screening for Learning Shared Feature Extractors
  5. ICML 2026On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
  6. ICML 2026On the Theory of Continual Learning with Gradient Descent for Neural Networks
  7. ICML 2026On the Variability of Concept Activation Vectors
  8. ICML 2026Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
  9. ICML 2026Optimal Learning from Label Proportions with General Loss Functions
  10. ICML 2026Optimal Stopping in Latent Diffusion Models
  11. ICML 2026Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
  12. ICML 2026PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
  13. ICML 2026PCA of Probability Measures: Sparse and Dense Sampling Regimes
  14. ICML 2026Performative Learning Theory
  15. ICML 2026Positive Distribution Shift as a Framework for Understanding Tractable Learning
  16. ICML 2026Provable Bounds for the Learnability of Sample-Compressible Families from Noisy Samples
  17. ICML 2026Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
  18. ICML 2026Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
  19. ICML 2026Provably Label-Efficient Conformal Prediction
  20. ICML 2026Provably Learning Attention with Queries
  21. ICML 2026Rational Neural Networks have Expressivity Advantages
  22. ICML 2026Rational Transductors
  23. ICML 2026Realizable Bayes-Consistency for General Metric Losses
  24. ICML 2026Refined Analysis of Entropy-Regularized Actor-Critic
  25. ICML 2026Representation Learning for Equivariant Inference with Guarantees
  26. ICML 2026Revisiting the Volume Hypothesis
  27. ICML 2026Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
  28. ICML 2026SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator
  29. ICML 2026Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
  30. ICML 2026Scaling Laws for Precision in High-Dimensional Linear Regression
  31. ICML 2026Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees
  32. ICML 2026Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
  33. ICML 2026Sharp Empirical Bernstein Inequalities for the Variance of Bounded Random Variables
  34. ICML 2026Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures
  35. ICML 2026Sharper Generalization Guarantees for Asynchronous SGD: Beyond Lipschitzness, Smoothness and Data Homogeneity
  36. ICML 2026Sparse Regression with $\ell_0$ Constraints for $\alpha$-Mixing Time Series: Algorithms and Guarantees
  37. ICML 2026Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
  38. ICML 2026Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
  39. ICML 2026Statistical Consistency and Generalization of Contrastive Representation Learning
  40. ICML 2026Statistically Undetectable Backdoors in Deep Neural Networks
  41. ICML 2026The Catastrophic Failure of *the* k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It
  42. ICML 2026The Data Manifold under the Microscope
  43. ICML 2026The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
  44. ICML 2026The Entropic Signature of Class Speciation in Diffusion Models
  45. ICML 2026The Fisher Dimension: Instance-Dependent Complexity for Causal Discovery
  46. ICML 2026The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
  47. ICML 2026The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity
  48. ICML 2026The Optimal Sample Complexity of Linear Contracts
  49. ICML 2026The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
  50. ICML 2026Theoretical Investigation on Inductive Bias of Isolation Forest

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