理论 · learning theory论文趋势 2023–2026

主要结论

• 理论 · learning theory论文从 2023 年的 86 篇增长到 2026 年的 482 篇，三年间扩大到约 5.6 倍。
• NeurIPS 是发理论 · learning theory论文最多的会议，2023–2026 年共 540 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 33 篇。
• 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的理论 · optimization是 4.7 倍，理论 · learning theory是 5.6 倍。

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

• NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
• ICML 2026A Fine-Grained Understanding of Uniform Convergence for Halfspaces
• ICLR 2026A Law of Data Reconstruction for Random Features (And Beyond)
• NeurIPS 2025A Geometric Analysis of PCA
• ICML 2025A Generalization Theory for Zero-Shot Prediction
• ICLR 2025A Solvable Attention for Neural Scaling Laws
• CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
• NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
• ICML 2024A Statistical Theory of Regularization-Based Continual Learning
• ICLR 2024A Sublinear Adversarial Training Algorithm
• CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
• ICLR 2023Bispectral Neural Networks
• NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
• ICML 2026A Random Matrix Theory of Masked Self-Supervised Learning
• ICLR 2026A New Approach to Controlling Linear Dynamical Systems
• NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
• ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
• ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

全部理论 · learning theory论文

共 86 篇，第 2 / 2 页

51. NeurIPS 2023Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
52. NeurIPS 2023Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
53. NeurIPS 2023Max-Sliced Mutual Information
54. NeurIPS 2023Nash Regret Guarantees for Linear Bandits
55. NeurIPS 2023Near-Linear Time Algorithm for the Chamfer Distance
56. NeurIPS 2023New Bounds for Hyperparameter Tuning of Regression Problems Across Instances
57. NeurIPS 2023No-regret Algorithms for Fair Resource Allocation
58. NeurIPS 2023On Generalization Bounds for Projective Clustering
59. NeurIPS 2023On kernel-based statistical learning theory in the mean field limit
60. NeurIPS 2023On Slicing Optimality for Mutual Information
61. NeurIPS 2023On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
62. NeurIPS 2023Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games
63. NeurIPS 2023Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
64. NeurIPS 2023Provable benefits of score matching
65. NeurIPS 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraints
66. NeurIPS 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework
67. NeurIPS 2023Reliable learning in challenging environments
68. NeurIPS 2023Replicability in Reinforcement Learning
69. NeurIPS 2023Replicable Clustering
70. NeurIPS 2023Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
71. NeurIPS 2023Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms
72. NeurIPS 2023Sharp Spectral Rates for Koopman Operator Learning
73. NeurIPS 2023Similarity-based cooperative equilibrium
74. NeurIPS 2023Smoothed Analysis of Sequential Probability Assignment
75. NeurIPS 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
76. NeurIPS 2023Strategic Data Sharing between Competitors
77. NeurIPS 2023Structured Prediction with Stronger Consistency Guarantees
78. NeurIPS 2023Temporally Disentangled Representation Learning under Unknown Nonstationarity
79. NeurIPS 2023The Crucial Role of Normalization in Sharpness-Aware Minimization
80. NeurIPS 2023The noise level in linear regression with dependent data
81. NeurIPS 2023Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
82. NeurIPS 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
83. NeurIPS 2023Two-Stage Learning to Defer with Multiple Experts
84. NeurIPS 2023What can a Single Attention Layer Learn? A Study Through the Random Features Lens
85. NeurIPS 2023When are ensembles really effective?
86. NeurIPS 2023Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria

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。