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 482 篇，第 8 / 10 页

  1. ICML 2026Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
  2. ICML 2026Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets
  3. ICML 2026Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
  4. ICML 2026To Grok Grokking: Provable Grokking in Ridge Regression
  5. ICML 2026Token Sample Complexity of Attention
  6. ICML 2026Towards Atoms of Large Language Models
  7. ICML 2026Towards Spectroscopy: Susceptibility Clusters in Language Models
  8. ICML 2026Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
  9. ICML 2026Towards Understanding Generalization of Federated Adversarial Learning: Perspective of Algorithmic Stability
  10. ICML 2026Trajectory Seriation via Spectral Tangent Alignment and Global Embedding
  11. ICML 2026Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
  12. ICML 2026Understanding Generalization from Embedding Dimension and Distributional Convergence
  13. ICML 2026Understanding Private Learning From Feature Perspective
  14. ICML 2026Unifying Low Dimensional Spectra in Deep Learning
  15. ICML 2026Universal Learning of Nonlinear Dynamics
  16. ICML 2026Universal Multiclass Transductive Online Learning
  17. ICML 2026What Does Preference Learning Recover from Pairwise Comparison Data?
  18. ICML 2026Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models
  19. ICML 2026Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
  20. ICML 2026Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting
  21. NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
  22. NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
  23. NeurIPS 2026A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
  24. NeurIPS 2026A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
  25. NeurIPS 2026A Theory of Adversary-Directed Online Learning
  26. NeurIPS 2026A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
  27. NeurIPS 2026A Theory of Training Profit-Optimal LLMs
  28. NeurIPS 2026A Theory on Flow Matching with Neural Networks
  29. NeurIPS 2026A Unified Spectral Theory of Multimodal Losses
  30. NeurIPS 2026Adaptive Calibration in Non-Stationary Environments
  31. NeurIPS 2026An exact information theory of generalization phase transitions in Bayesian diffusion models
  32. NeurIPS 2026Approximate Envy-Free Allocations up to any k Goods
  33. NeurIPS 2026Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
  34. NeurIPS 2026Avoiding Obfuscation with Prover-Estimator Debate
  35. NeurIPS 2026Best Arm Identification for Bandits with Shifting Means
  36. NeurIPS 2026Bilinear Matching Bandits
  37. NeurIPS 2026Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
  38. NeurIPS 2026Borda-Based Fair Multi-User Dueling Bandit in Tabular and Generalized Linear Settings
  39. NeurIPS 2026Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications
  40. NeurIPS 2026Chain of Dual Structures in Transformer Attention
  41. NeurIPS 2026Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator
  42. NeurIPS 2026Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine
  43. NeurIPS 2026Constrained MDPs with Trajectory Constraints
  44. NeurIPS 2026Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization
  45. NeurIPS 2026Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations
  46. NeurIPS 2026Decentralized Coupled Representation Learning
  47. NeurIPS 2026Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
  48. NeurIPS 2026Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
  49. NeurIPS 2026Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits
  50. NeurIPS 2026Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence

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