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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 57 | 24 | 5 | 0 | 86 |
| 2024 | 265 | 106 | 21 | 1 | 393 |
| 2025 | 106 | 147 | 132 | 4 | 389 |
| 2026 | 112 | 200 | 170 | 0 | 482 |
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 477 篇，第 6 / 10 页
- ICLR 2025Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging
- ICLR 2025Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
- ICLR 2025Generalized Principal-Agent Problem with a Learning Agent
- ICLR 2025Geometry of Lightning Self-Attention: Identifiability and Dimension
- ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
- ICLR 2025Grokking at the Edge of Numerical Stability
- ICLR 2025How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
- ICLR 2025How Feature Learning Can Improve Neural Scaling Laws
- ICLR 2025How Gradient descent balances features: A dynamical analysis for two-layer neural networks
- ICLR 2025How many samples are needed to train a deep neural network?
- ICLR 2025How Much is Unseen Depends Chiefly on Information About the Seen
- ICLR 2025Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions
- ICLR 2025Improved Convergence Rate for Diffusion Probabilistic Models
- ICLR 2025Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent
- ICLR 2025Inner Information Analysis Algorithm for Deep Neural Network based on Community
- ICLR 2025Lambda-Skip Connections: the architectural component that prevents Rank Collapse
- ICLR 2025Lasso Bandit with Compatibility Condition on Optimal Arm
- ICLR 2025Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
- ICLR 2025Learning from weak labelers as constraints
- ICLR 2025Learning Hierarchical Polynomials of Multiple Nonlinear Features
- ICLR 2025Learning High-Degree Parities: The Crucial Role of the Initialization
- ICLR 2025Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
- ICLR 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
- ICLR 2025Learning to Help in Multi-Class Settings
- ICLR 2025Learning-Augmented Search Data Structures
- ICLR 2025Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model
- ICLR 2025Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
- ICLR 2025Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory
- ICLR 2025Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data
- ICLR 2025Lipschitz Bandits in Optimal Space
- ICLR 2025Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
- ICLR 2025MAST: model-agnostic sparsified training
- ICLR 2025Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
- ICLR 2025Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift
- ICLR 2025Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
- ICLR 2025Near-optimal Active Regression of Single-Index Models
- ICLR 2025No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
- ICLR 2025O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions
- ICLR 2025On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions
- ICLR 2025On the expressiveness and spectral bias of KANs
- ICLR 2025On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
- ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
- ICLR 2025On the Optimal Memorization Capacity of Transformers
- ICLR 2025On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
- ICLR 2025On the Relation between Trainability and Dequantization of Variational Quantum Learning Models
- ICLR 2025ONLINE EPSILON NET & PIERCING SET FOR GEOMETRIC CONCEPTS
- ICLR 2025Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios
- ICLR 2025Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
- ICLR 2025Oracle efficient truncated statistics
- ICLR 2025Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors
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"}
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。