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 393 篇，第 3 / 8 页

101. ICLR 2024Toward Student-oriented Teacher Network Training for Knowledge Distillation
102. ICLR 2024Towards Establishing Guaranteed Error for Learned Database Operations
103. ICLR 2024Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
104. ICLR 2024Towards the Fundamental Limits of Knowledge Transfer over Finite Domains
105. ICLR 2024Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
106. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
107. ICLR 2024When can transformers reason with abstract symbols?
108. ICML 2024A sampling theory perspective on activations for implicit neural representations
109. ICML 2024A Statistical Theory of Regularization-Based Continual Learning
110. ICML 2024A Theory of Fault-Tolerant Learning
111. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
112. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
113. ICML 2024Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
114. ICML 2024Matrix Information Theory for Self-Supervised Learning
115. ICML 2024Minimum Norm Interpolation Meets The Local Theory of Banach Spaces
116. ICML 2024On Statistical Learning Theory for Distributional Inputs
117. ICML 2024Open Ad Hoc Teamwork with Cooperative Game Theory
118. ICML 2024PIDformer: Transformer Meets Control Theory
119. ICML 2024Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
120. ICML 2024Position: Future Directions in the Theory of Graph Machine Learning
121. ICML 2024Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory
122. ICML 2024Random matrix theory improved Fréchet mean of symmetric positive definite matrices
123. ICML 2024Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
124. ICML 2024Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction
125. ICML 2024Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
126. ICML 2024Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling
127. ICML 2024Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
128. ICML 2024Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models
129. NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
130. NeurIPS 2024A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
131. NeurIPS 2024A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
132. NeurIPS 2024A Kernel Perspective on Distillation-based Collaborative Learning
133. NeurIPS 2024A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
134. NeurIPS 2024A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
135. NeurIPS 2024A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
136. NeurIPS 2024A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
137. NeurIPS 2024A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
138. NeurIPS 2024A Theory of Optimistically Universal Online Learnability for General Concept Classes
139. NeurIPS 2024A two-scale Complexity Measure for Deep Learning Models
140. NeurIPS 2024A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
141. NeurIPS 2024A Universal Growth Rate for Learning with Smooth Surrogate Losses
142. NeurIPS 2024Accelerating ERM for data-driven algorithm design using output-sensitive techniques
143. NeurIPS 2024Accelerating Relative Entropy Coding with Space Partitioning
144. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
145. NeurIPS 2024Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
146. NeurIPS 2024Active Classification with Few Queries under Misspecification
147. NeurIPS 2024Active Learning of General Halfspaces: Label Queries vs Membership Queries
148. NeurIPS 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
149. NeurIPS 2024Adversarially Robust Multi-task Representation Learning
150. NeurIPS 2024Algebraic Positional Encodings

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。