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 200 篇，第 4 / 4 页

  1. ICLR 2026Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
  2. ICLR 2026Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
  3. ICLR 2026Semi-Parametric Contextual Pricing with General Smoothness
  4. ICLR 2026Sequences of Logits Reveal the Low Rank Structure of Language Models
  5. ICLR 2026SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
  6. ICLR 2026Sharp asymptotic theory for Q-learning with \texttt{LD2Z} learning rate and its generalization
  7. ICLR 2026Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions
  8. ICLR 2026Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis
  9. ICLR 2026Stable coresets: Unleashing the power of uniform sampling
  10. ICLR 2026Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
  11. ICLR 2026Sublinear Spectral Clustering Oracle with Little Memory
  12. ICLR 2026Subquadratic Algorithms and Hardness for Attention with Any Temperature
  13. ICLR 2026SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
  14. ICLR 2026Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
  15. ICLR 2026The Coverage Principle: How Pre-Training Enables Post-Training
  16. ICLR 2026The Effect of Attention Head Count on Transformer Approximation
  17. ICLR 2026The Expressive Limits of Diagonal SSMs for State-Tracking
  18. ICLR 2026The Price of Robustness: Stable Classifiers Need Overparameterization
  19. ICLR 2026The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
  20. ICLR 2026The Serial Scaling Hypothesis
  21. ICLR 2026Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution
  22. ICLR 2026Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
  23. ICLR 2026Tight Bounds for Schrodinger Potential Estimation in Unpaired Data Translation
  24. ICLR 2026Tighter Performance Theory of FedExProx
  25. ICLR 2026Topology and geometry of the learning space of ReLU networks: connectivity and singularities
  26. ICLR 2026Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections
  27. ICLR 2026Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual Bandits
  28. ICLR 2026Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D Generalisation
  29. ICLR 2026Towards a Universally Transferable Acceleration Method for Density Functional Theory
  30. ICLR 2026Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks
  31. ICLR 2026Training-Free Determination of Network Width via Neural Tangent Kernel
  32. ICLR 2026Transfer Learning in Infinite Width Feature Learning Networks
  33. ICLR 2026Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
  34. ICLR 2026Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures
  35. ICLR 2026Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
  36. ICLR 2026Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation
  37. ICLR 2026Tuning the burn-in phase in training recurrent neural networks improves their performance
  38. ICLR 2026Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
  39. ICLR 2026Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen Anomalies
  40. ICLR 2026Unbiased Gradient Estimation for Event Binning via Functional Backpropagation
  41. ICLR 2026Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent Kernel
  42. ICLR 2026Understanding the Role of Training Data in Test-Time Scaling
  43. ICLR 2026Variational Inference for Cyclic Learning
  44. ICLR 2026Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
  45. ICLR 2026When Bias Helps Learning: Bridging Initial Prejudice and Trainability
  46. ICLR 2026When Flatness Does (Not) Guarantee Adversarial Robustness
  47. ICLR 2026When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
  48. ICLR 2026Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
  49. ICLR 2026Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
  50. ICLR 2026Why Less is More (Sometimes): A Theory of Data Curation

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