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 11 / 27 页

  1. ICLR 2025Attention layers provably solve single-location regression
  2. ICLR 2025Bandit Learning in Matching Markets with Indifference
  3. ICLR 2025Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural Networks
  4. ICLR 2025Benign Overfitting in Out-of-Distribution Generalization of Linear Models
  5. ICLR 2025Binary Losses for Density Ratio Estimation
  6. ICLR 2025Block Verification Accelerates Speculative Decoding
  7. ICLR 2025Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions
  8. ICLR 2025Bridging the Gap Between f-divergences and Bayes Hilbert Spaces
  9. ICLR 2025Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
  10. ICLR 2025Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model
  11. ICLR 2025Can One Modality Model Synergize Training of Other Modality Models?
  12. ICLR 2025Chain-of-Thought Provably Enables Learning the (Otherwise) Unlearnable
  13. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
  14. ICLR 2025Computational Explorations of Total Variation Distance
  15. ICLR 2025Compute-Optimal LLMs Provably Generalize Better with Scale
  16. ICLR 2025Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation
  17. ICLR 2025Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information
  18. ICLR 2025Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
  19. ICLR 2025Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees
  20. ICLR 2025Decomposition Polyhedra of Piecewise Linear Functions
  21. ICLR 2025Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
  22. ICLR 2025Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
  23. ICLR 2025Distribution-Specific Agnostic Conditional Classification With Halfspaces
  24. ICLR 2025Divergence of Neural Tangent Kernel in Classification Problems
  25. ICLR 2025Dynamic Assortment Selection and Pricing with Censored Preference Feedback
  26. ICLR 2025Exact Community Recovery under Side Information: Optimality of Spectral Algorithms
  27. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
  28. ICLR 2025Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality
  29. ICLR 2025Extending Mercer's expansion to indefinite and asymmetric kernels
  30. ICLR 2025Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
  31. ICLR 2025Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
  32. ICLR 2025From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
  33. ICLR 2025From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
  34. ICLR 2025Fundamental Limitations on Subquadratic Alternatives to Transformers
  35. ICLR 2025Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power
  36. ICLR 2025Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks
  37. ICLR 2025Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging
  38. ICLR 2025Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
  39. ICLR 2025Generalized Principal-Agent Problem with a Learning Agent
  40. ICLR 2025Geometry of Lightning Self-Attention: Identifiability and Dimension
  41. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
  42. ICLR 2025Grokking at the Edge of Numerical Stability
  43. ICLR 2025How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
  44. ICLR 2025How Feature Learning Can Improve Neural Scaling Laws
  45. ICLR 2025How Gradient descent balances features: A dynamical analysis for two-layer neural networks
  46. ICLR 2025How many samples are needed to train a deep neural network?
  47. ICLR 2025How Much is Unseen Depends Chiefly on Information About the Seen
  48. ICLR 2025Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions
  49. ICLR 2025Improved Convergence Rate for Diffusion Probabilistic Models
  50. ICLR 2025Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

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